Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index f68c0c7..6a8db8e 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -352,6 +352,7 @@
 	unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
 	unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;
 	unsigned f_la57;
+	unsigned f_pku = kvm_x86_ops->pku_supported() ? F(PKU) : 0;
 
 	/* cpuid 7.0.ebx */
 	const u32 kvm_cpuid_7_0_ebx_x86_features =
@@ -363,7 +364,7 @@
 
 	/* cpuid 7.0.ecx*/
 	const u32 kvm_cpuid_7_0_ecx_x86_features =
-		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
+		F(AVX512VBMI) | F(LA57) | 0 /*PKU*/ | 0 /*OSPKE*/ | F(RDPID) |
 		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
 		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
 		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/;
@@ -392,6 +393,7 @@
 		/* Set LA57 based on hardware capability. */
 		entry->ecx |= f_la57;
 		entry->ecx |= f_umip;
+		entry->ecx |= f_pku;
 		/* PKU is not yet implemented for shadow paging. */
 		if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
 			entry->ecx &= ~F(PKU);
@@ -402,7 +404,8 @@
 			entry->edx |= F(SPEC_CTRL);
 		if (boot_cpu_has(X86_FEATURE_STIBP))
 			entry->edx |= F(INTEL_STIBP);
-		if (boot_cpu_has(X86_FEATURE_SSBD))
+		if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+		    boot_cpu_has(X86_FEATURE_AMD_SSBD))
 			entry->edx |= F(SPEC_CTRL_SSBD);
 		/*
 		 * We emulate ARCH_CAPABILITIES in software even
@@ -504,7 +507,7 @@
 
 	r = -E2BIG;
 
-	if (*nent >= maxnent)
+	if (WARN_ON(*nent >= maxnent))
 		goto out;
 
 	do_host_cpuid(entry, function, 0);
@@ -742,8 +745,14 @@
 		unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
 		unsigned phys_as = entry->eax & 0xff;
 
-		if (!g_phys_as)
+		/*
+		 * Use bare metal's MAXPHADDR if the CPU doesn't report guest
+		 * MAXPHYADDR separately, or if TDP (NPT) is disabled, as the
+		 * guest version "applies only to guests using nested paging".
+		 */
+		if (!g_phys_as || !tdp_enabled)
 			g_phys_as = phys_as;
+
 		entry->eax = g_phys_as | (virt_as << 8);
 		entry->edx = 0;
 		entry->ebx &= kvm_cpuid_8000_0008_ebx_x86_features;
@@ -759,7 +768,8 @@
 			entry->ebx |= F(AMD_IBRS);
 		if (boot_cpu_has(X86_FEATURE_STIBP))
 			entry->ebx |= F(AMD_STIBP);
-		if (boot_cpu_has(X86_FEATURE_SSBD))
+		if (boot_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+		    boot_cpu_has(X86_FEATURE_AMD_SSBD))
 			entry->ebx |= F(AMD_SSBD);
 		if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
 			entry->ebx |= F(AMD_SSB_NO);
@@ -810,6 +820,9 @@
 static int do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 func,
 			 int *nent, int maxnent, unsigned int type)
 {
+	if (*nent >= maxnent)
+		return -E2BIG;
+
 	if (type == KVM_GET_EMULATED_CPUID)
 		return __do_cpuid_func_emulated(entry, func, nent, maxnent);
 
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index d78a614..7dec43b 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -154,6 +154,20 @@
 	return x86_stepping(best->eax);
 }
 
+static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu)
+{
+	return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
+		guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) ||
+		guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) ||
+		guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD));
+}
+
+static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu)
+{
+	return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
+		guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB));
+}
+
 static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.msr_platform_info & MSR_PLATFORM_INFO_CPUID_FAULT;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 698efb8..60c8dcb 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -22,6 +22,7 @@
 #include "kvm_cache_regs.h"
 #include <asm/kvm_emulate.h>
 #include <linux/stringify.h>
+#include <asm/fpu/api.h>
 #include <asm/debugreg.h>
 #include <asm/nospec-branch.h>
 
@@ -1075,8 +1076,23 @@
 	}
 }
 
+static void emulator_get_fpu(void)
+{
+	fpregs_lock();
+
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
+}
+
+static void emulator_put_fpu(void)
+{
+	fpregs_unlock();
+}
+
 static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
 	case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
@@ -1098,11 +1114,13 @@
 #endif
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
 static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 			  int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
 	case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
@@ -1124,10 +1142,12 @@
 #endif
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
 static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
 	case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
@@ -1139,10 +1159,12 @@
 	case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
 static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
+	emulator_get_fpu();
 	switch (reg) {
 	case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
 	case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
@@ -1154,6 +1176,7 @@
 	case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
 	default: BUG();
 	}
+	emulator_put_fpu();
 }
 
 static int em_fninit(struct x86_emulate_ctxt *ctxt)
@@ -1161,7 +1184,9 @@
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
+	emulator_get_fpu();
 	asm volatile("fninit");
+	emulator_put_fpu();
 	return X86EMUL_CONTINUE;
 }
 
@@ -1172,7 +1197,9 @@
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
+	emulator_get_fpu();
 	asm volatile("fnstcw %0": "+m"(fcw));
+	emulator_put_fpu();
 
 	ctxt->dst.val = fcw;
 
@@ -1186,7 +1213,9 @@
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
+	emulator_get_fpu();
 	asm volatile("fnstsw %0": "+m"(fsw));
+	emulator_put_fpu();
 
 	ctxt->dst.val = fsw;
 
@@ -2861,6 +2890,8 @@
 	ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data);
 	*reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data :
 							      (u32)msr_data;
+	if (efer & EFER_LMA)
+		ctxt->mode = X86EMUL_MODE_PROT64;
 
 	return X86EMUL_CONTINUE;
 }
@@ -3588,7 +3619,7 @@
 	u64 tsc_aux = 0;
 
 	if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux))
-		return emulate_gp(ctxt, 0);
+		return emulate_ud(ctxt);
 	ctxt->dst.val = tsc_aux;
 	return X86EMUL_CONTINUE;
 }
@@ -4021,6 +4052,12 @@
 	return X86EMUL_CONTINUE;
 }
 
+static int em_clflushopt(struct x86_emulate_ctxt *ctxt)
+{
+	/* emulating clflushopt regardless of cpuid */
+	return X86EMUL_CONTINUE;
+}
+
 static int em_movsxd(struct x86_emulate_ctxt *ctxt)
 {
 	ctxt->dst.val = (s32) ctxt->src.val;
@@ -4094,8 +4131,12 @@
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
+	emulator_get_fpu();
+
 	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
 
+	emulator_put_fpu();
+
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -4138,6 +4179,8 @@
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
+	emulator_get_fpu();
+
 	if (size < __fxstate_size(16)) {
 		rc = fxregs_fixup(&fx_state, size);
 		if (rc != X86EMUL_CONTINUE)
@@ -4153,6 +4196,8 @@
 		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
 
 out:
+	emulator_put_fpu();
+
 	return rc;
 }
 
@@ -4555,7 +4600,7 @@
 };
 
 static const struct gprefix pfx_0f_ae_7 = {
-	I(SrcMem | ByteOp, em_clflush), N, N, N,
+	I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N,
 };
 
 static const struct group_dual group15 = { {
@@ -5160,6 +5205,7 @@
 	ctxt->fetch.ptr = ctxt->fetch.data;
 	ctxt->fetch.end = ctxt->fetch.data + insn_len;
 	ctxt->opcode_len = 1;
+	ctxt->intercept = x86_intercept_none;
 	if (insn_len > 0)
 		memcpy(ctxt->fetch.data, insn, insn_len);
 	else {
@@ -5212,16 +5258,28 @@
 				ctxt->ad_bytes = def_ad_bytes ^ 6;
 			break;
 		case 0x26:	/* ES override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_ES;
+			break;
 		case 0x2e:	/* CS override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_CS;
+			break;
 		case 0x36:	/* SS override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_SS;
+			break;
 		case 0x3e:	/* DS override */
 			has_seg_override = true;
-			ctxt->seg_override = (ctxt->b >> 3) & 3;
+			ctxt->seg_override = VCPU_SREG_DS;
 			break;
 		case 0x64:	/* FS override */
+			has_seg_override = true;
+			ctxt->seg_override = VCPU_SREG_FS;
+			break;
 		case 0x65:	/* GS override */
 			has_seg_override = true;
-			ctxt->seg_override = ctxt->b & 7;
+			ctxt->seg_override = VCPU_SREG_GS;
 			break;
 		case 0x40 ... 0x4f: /* REX */
 			if (mode != X86EMUL_MODE_PROT64)
@@ -5305,10 +5363,15 @@
 			}
 			break;
 		case Escape:
-			if (ctxt->modrm > 0xbf)
-				opcode = opcode.u.esc->high[ctxt->modrm - 0xc0];
-			else
+			if (ctxt->modrm > 0xbf) {
+				size_t size = ARRAY_SIZE(opcode.u.esc->high);
+				u32 index = array_index_nospec(
+					ctxt->modrm - 0xc0, size);
+
+				opcode = opcode.u.esc->high[index];
+			} else {
 				opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
+			}
 			break;
 		case InstrDual:
 			if ((ctxt->modrm >> 6) == 3)
@@ -5450,7 +5513,9 @@
 {
 	int rc;
 
+	emulator_get_fpu();
 	rc = asm_safe("fwait");
+	emulator_put_fpu();
 
 	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
@@ -5779,6 +5844,8 @@
 	}
 
 	ctxt->eip = ctxt->_eip;
+	if (ctxt->mode != X86EMUL_MODE_PROT64)
+		ctxt->eip = (u32)ctxt->_eip;
 
 done:
 	if (rc == X86EMUL_PROPAGATE_FAULT) {
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 23ff655..2640843 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -809,11 +809,12 @@
 				     u32 index, u64 *pdata)
 {
 	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+	size_t size = ARRAY_SIZE(hv->hv_crash_param);
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+	if (WARN_ON_ONCE(index >= size))
 		return -EINVAL;
 
-	*pdata = hv->hv_crash_param[index];
+	*pdata = hv->hv_crash_param[array_index_nospec(index, size)];
 	return 0;
 }
 
@@ -852,11 +853,12 @@
 				     u32 index, u64 data)
 {
 	struct kvm_hv *hv = &vcpu->kvm->arch.hyperv;
+	size_t size = ARRAY_SIZE(hv->hv_crash_param);
 
-	if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param)))
+	if (WARN_ON_ONCE(index >= size))
 		return -EINVAL;
 
-	hv->hv_crash_param[index] = data;
+	hv->hv_crash_param[array_index_nospec(index, size)] = data;
 	return 0;
 }
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 8b38bb4..629a09c 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -460,10 +460,14 @@
 	switch (addr) {
 	case 0x20:
 	case 0x21:
+		pic_lock(s);
+		pic_ioport_write(&s->pics[0], addr, data);
+		pic_unlock(s);
+		break;
 	case 0xa0:
 	case 0xa1:
 		pic_lock(s);
-		pic_ioport_write(&s->pics[addr >> 7], addr, data);
+		pic_ioport_write(&s->pics[1], addr, data);
 		pic_unlock(s);
 		break;
 	case 0x4d0:
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index d859ae8..642031b 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -36,6 +36,7 @@
 #include <linux/io.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/nospec.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/current.h>
@@ -68,13 +69,14 @@
 	default:
 		{
 			u32 redir_index = (ioapic->ioregsel - 0x10) >> 1;
-			u64 redir_content;
+			u64 redir_content = ~0ULL;
 
-			if (redir_index < IOAPIC_NUM_PINS)
-				redir_content =
-					ioapic->redirtbl[redir_index].bits;
-			else
-				redir_content = ~0ULL;
+			if (redir_index < IOAPIC_NUM_PINS) {
+				u32 index = array_index_nospec(
+					redir_index, IOAPIC_NUM_PINS);
+
+				redir_content = ioapic->redirtbl[index].bits;
+			}
 
 			result = (ioapic->ioregsel & 0x1) ?
 			    (redir_content >> 32) & 0xffffffff :
@@ -89,7 +91,7 @@
 static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
 {
 	ioapic->rtc_status.pending_eoi = 0;
-	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
+	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1);
 }
 
 static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
@@ -291,6 +293,7 @@
 
 		if (index >= IOAPIC_NUM_PINS)
 			return;
+		index = array_index_nospec(index, IOAPIC_NUM_PINS);
 		e = &ioapic->redirtbl[index];
 		mask_before = e->fields.mask;
 		/* Preserve read-only fields */
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index ea1a4e0..283f1f4 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -43,13 +43,13 @@
 
 struct dest_map {
 	/* vcpu bitmap where IRQ has been sent */
-	DECLARE_BITMAP(map, KVM_MAX_VCPU_ID);
+	DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1);
 
 	/*
 	 * Vector sent to a given vcpu, only valid when
 	 * the vcpu's bit in map is set
 	 */
-	u8 vectors[KVM_MAX_VCPU_ID];
+	u8 vectors[KVM_MAX_VCPU_ID + 1];
 };
 
 
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index e330e7d..896db1a 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -40,29 +40,10 @@
  * check if there is pending interrupt from
  * non-APIC source without intack.
  */
-static int kvm_cpu_has_extint(struct kvm_vcpu *v)
-{
-	u8 accept = kvm_apic_accept_pic_intr(v);
-
-	if (accept) {
-		if (irqchip_split(v->kvm))
-			return pending_userspace_extint(v);
-		else
-			return v->kvm->arch.vpic->output;
-	} else
-		return 0;
-}
-
-/*
- * check if there is injectable interrupt:
- * when virtual interrupt delivery enabled,
- * interrupt from apic will handled by hardware,
- * we don't need to check it here.
- */
-int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+int kvm_cpu_has_extint(struct kvm_vcpu *v)
 {
 	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
+	 * FIXME: interrupt.injected represents an interrupt whose
 	 * side-effects have already been applied (e.g. bit from IRR
 	 * already moved to ISR). Therefore, it is incorrect to rely
 	 * on interrupt.injected to know if there is a pending
@@ -75,6 +56,23 @@
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.injected;
 
+	if (!kvm_apic_accept_pic_intr(v))
+		return 0;
+
+	if (irqchip_split(v->kvm))
+		return pending_userspace_extint(v);
+	else
+		return v->kvm->arch.vpic->output;
+}
+
+/*
+ * check if there is injectable interrupt:
+ * when virtual interrupt delivery enabled,
+ * interrupt from apic will handled by hardware,
+ * we don't need to check it here.
+ */
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+{
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -90,20 +88,6 @@
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
-	 * side-effects have already been applied (e.g. bit from IRR
-	 * already moved to ISR). Therefore, it is incorrect to rely
-	 * on interrupt.injected to know if there is a pending
-	 * interrupt in the user-mode LAPIC.
-	 * This leads to nVMX/nSVM not be able to distinguish
-	 * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on
-	 * pending interrupt or should re-inject an injected
-	 * interrupt.
-	 */
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.injected;
-
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -117,16 +101,21 @@
  */
 static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 {
-	if (kvm_cpu_has_extint(v)) {
-		if (irqchip_split(v->kvm)) {
-			int vector = v->arch.pending_external_vector;
-
-			v->arch.pending_external_vector = -1;
-			return vector;
-		} else
-			return kvm_pic_read_irq(v->kvm); /* PIC */
-	} else
+	if (!kvm_cpu_has_extint(v)) {
+		WARN_ON(!lapic_in_kernel(v));
 		return -1;
+	}
+
+	if (!lapic_in_kernel(v))
+		return v->arch.interrupt.nr;
+
+	if (irqchip_split(v->kvm)) {
+		int vector = v->arch.pending_external_vector;
+
+		v->arch.pending_external_vector = -1;
+		return vector;
+	} else
+		return kvm_pic_read_irq(v->kvm); /* PIC */
 }
 
 /*
@@ -134,13 +123,7 @@
  */
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 {
-	int vector;
-
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.nr;
-
-	vector = kvm_cpu_get_extint(v);
-
+	int vector = kvm_cpu_get_extint(v);
 	if (vector != -1)
 		return vector;			/* PIC */
 
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 8ecd48d..5ddcaac 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -416,7 +416,7 @@
 
 			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
-			if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0,
+			if (irq.trig_mode && kvm_apic_match_dest(vcpu, NULL, 0,
 						irq.dest_id, irq.dest_mode))
 				__set_bit(irq.vector, ioapic_handled_vectors);
 		}
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 1cc6c47..341f58a 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -7,7 +7,7 @@
 #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
 #define KVM_POSSIBLE_CR4_GUEST_BITS				  \
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
+	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD)
 
 #define BUILD_KVM_GPR_ACCESSORS(lname, uname)				      \
 static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b29d00b..eea2d6f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -637,9 +637,11 @@
 static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)
 {
 	u8 val;
-	if (pv_eoi_get_user(vcpu, &val) < 0)
+	if (pv_eoi_get_user(vcpu, &val) < 0) {
 		printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n",
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
+		return false;
+	}
 	return val & 0x1;
 }
 
@@ -1056,11 +1058,8 @@
 						       apic->regs + APIC_TMR);
 		}
 
-		if (vcpu->arch.apicv_active)
-			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
-		else {
+		if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) {
 			kvm_lapic_set_irr(vector, apic);
-
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}
@@ -1333,6 +1332,9 @@
 	if (!apic_x2apic_mode(apic))
 		valid_reg_mask |= APIC_REG_MASK(APIC_ARBPRI);
 
+	if (alignment + len > 4)
+		return 1;
+
 	if (offset > 0x3f0 || !(valid_reg_mask & APIC_REG_MASK(offset)))
 		return 1;
 
@@ -1685,7 +1687,7 @@
 
 	hrtimer_start(&apic->lapic_timer.timer,
 		apic->lapic_timer.target_expiration,
-		HRTIMER_MODE_ABS);
+		HRTIMER_MODE_ABS_HARD);
 }
 
 bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu)
@@ -1926,15 +1928,20 @@
 	case APIC_LVTTHMR:
 	case APIC_LVTPC:
 	case APIC_LVT1:
-	case APIC_LVTERR:
+	case APIC_LVTERR: {
 		/* TODO: Check vector */
+		size_t size;
+		u32 index;
+
 		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
-
-		val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4];
+		size = ARRAY_SIZE(apic_lvt_mask);
+		index = array_index_nospec(
+				(reg - APIC_LVTT) >> 4, size);
+		val &= apic_lvt_mask[index];
 		kvm_lapic_set_reg(apic, reg, val);
-
 		break;
+	}
 
 	case APIC_LVTT:
 		if (!kvm_apic_sw_enabled(apic))
@@ -2081,7 +2088,7 @@
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
+	if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) ||
 			apic_lvtt_period(apic))
 		return;
 
@@ -2326,7 +2333,7 @@
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 ppr;
 
-	if (!kvm_apic_hw_enabled(apic))
+	if (!kvm_apic_present(vcpu))
 		return -1;
 
 	__apic_update_ppr(apic, &ppr);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 2ce9da5..d3877dd 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -343,6 +343,8 @@
 {
 	BUG_ON((u64)(unsigned)access_mask != access_mask);
 	BUG_ON((mmio_mask & mmio_value) != mmio_value);
+	WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len));
+	WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
 	shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
 	shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
 	shadow_mmio_access_mask = access_mask;
@@ -405,11 +407,11 @@
 }
 
 /*
- * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of
+ * Due to limited space in PTEs, the MMIO generation is a 18 bit subset of
  * the memslots generation and is derived as follows:
  *
  * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11
- * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61
+ * Bits 9-17 of the MMIO generation are propagated to spte bits 54-62
  *
  * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in
  * the MMIO generation number, as doing so would require stealing a bit from
@@ -418,25 +420,38 @@
  * requires a full MMU zap).  The flag is instead explicitly queried when
  * checking for MMIO spte cache hits.
  */
-#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(18, 0)
 
 #define MMIO_SPTE_GEN_LOW_START		3
 #define MMIO_SPTE_GEN_LOW_END		11
+
+#define MMIO_SPTE_GEN_HIGH_START	PT64_SECOND_AVAIL_BITS_SHIFT
+#define MMIO_SPTE_GEN_HIGH_END		62
+
 #define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
 						    MMIO_SPTE_GEN_LOW_START)
-
-#define MMIO_SPTE_GEN_HIGH_START	52
-#define MMIO_SPTE_GEN_HIGH_END		61
 #define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
 						    MMIO_SPTE_GEN_HIGH_START)
+
+#define MMIO_SPTE_GEN_LOW_BITS		(MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1)
+#define MMIO_SPTE_GEN_HIGH_BITS		(MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1)
+
+/* remember to adjust the comment above as well if you change these */
+static_assert(MMIO_SPTE_GEN_LOW_BITS == 9 && MMIO_SPTE_GEN_HIGH_BITS == 9);
+
+#define MMIO_SPTE_GEN_LOW_SHIFT		(MMIO_SPTE_GEN_LOW_START - 0)
+#define MMIO_SPTE_GEN_HIGH_SHIFT	(MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS)
+
+#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
+
 static u64 generation_mmio_spte_mask(u64 gen)
 {
 	u64 mask;
 
 	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
+	BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK);
 
-	mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK;
-	mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK;
+	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
+	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
 	return mask;
 }
 
@@ -444,10 +459,8 @@
 {
 	u64 gen;
 
-	spte &= ~shadow_mmio_mask;
-
-	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START;
-	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START;
+	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT;
+	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT;
 	return gen;
 }
 
@@ -538,16 +551,20 @@
 static u8 kvm_get_shadow_phys_bits(void)
 {
 	/*
-	 * boot_cpu_data.x86_phys_bits is reduced when MKTME is detected
-	 * in CPU detection code, but MKTME treats those reduced bits as
-	 * 'keyID' thus they are not reserved bits. Therefore for MKTME
-	 * we should still return physical address bits reported by CPUID.
+	 * boot_cpu_data.x86_phys_bits is reduced when MKTME or SME are detected
+	 * in CPU detection code, but the processor treats those reduced bits as
+	 * 'keyID' thus they are not reserved bits. Therefore KVM needs to look at
+	 * the physical address bits reported by CPUID.
 	 */
-	if (!boot_cpu_has(X86_FEATURE_TME) ||
-	    WARN_ON_ONCE(boot_cpu_data.extended_cpuid_level < 0x80000008))
-		return boot_cpu_data.x86_phys_bits;
+	if (likely(boot_cpu_data.extended_cpuid_level >= 0x80000008))
+		return cpuid_eax(0x80000008) & 0xff;
 
-	return cpuid_eax(0x80000008) & 0xff;
+	/*
+	 * Quite weird to have VMX or SVM but not MAXPHYADDR; probably a VM with
+	 * custom CPUID.  Proceed with whatever the kernel found since these features
+	 * aren't virtualizable (SME/SEV also require CPUIDs higher than 0x80000008).
+	 */
+	return boot_cpu_data.x86_phys_bits;
 }
 
 static void kvm_mmu_reset_all_pte_masks(void)
@@ -576,16 +593,15 @@
 	 * the most significant bits of legal physical address space.
 	 */
 	shadow_nonpresent_or_rsvd_mask = 0;
-	low_phys_bits = boot_cpu_data.x86_cache_bits;
-	if (boot_cpu_data.x86_cache_bits <
-	    52 - shadow_nonpresent_or_rsvd_mask_len) {
+	low_phys_bits = boot_cpu_data.x86_phys_bits;
+	if (boot_cpu_has_bug(X86_BUG_L1TF) &&
+	    !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
+			  52 - shadow_nonpresent_or_rsvd_mask_len)) {
+		low_phys_bits = boot_cpu_data.x86_cache_bits
+			- shadow_nonpresent_or_rsvd_mask_len;
 		shadow_nonpresent_or_rsvd_mask =
-			rsvd_bits(boot_cpu_data.x86_cache_bits -
-				  shadow_nonpresent_or_rsvd_mask_len,
-				  boot_cpu_data.x86_cache_bits - 1);
-		low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
-	} else
-		WARN_ON_ONCE(boot_cpu_has_bug(X86_BUG_L1TF));
+			rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
+	}
 
 	shadow_nonpresent_or_rsvd_lower_gfn_mask =
 		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
@@ -1282,12 +1298,12 @@
 	return __mmu_gfn_lpage_is_disallowed(gfn, level, slot);
 }
 
-static int host_mapping_level(struct kvm *kvm, gfn_t gfn)
+static int host_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
 	unsigned long page_size;
 	int i, ret = 0;
 
-	page_size = kvm_host_page_size(kvm, gfn);
+	page_size = kvm_host_page_size(vcpu, gfn);
 
 	for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		if (page_size >= KVM_HPAGE_SIZE(i))
@@ -1337,7 +1353,7 @@
 	if (unlikely(*force_pt_level))
 		return PT_PAGE_TABLE_LEVEL;
 
-	host_level = host_mapping_level(vcpu->kvm, large_gfn);
+	host_level = host_mapping_level(vcpu, large_gfn);
 
 	if (host_level == PT_PAGE_TABLE_LEVEL)
 		return host_level;
@@ -1814,10 +1830,10 @@
  * Emulate arch specific page modification logging for the
  * nested hypervisor
  */
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
 {
 	if (kvm_x86_ops->write_log_dirty)
-		return kvm_x86_ops->write_log_dirty(vcpu);
+		return kvm_x86_ops->write_log_dirty(vcpu, l2_gpa);
 
 	return 0;
 }
@@ -2040,7 +2056,8 @@
 	return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
 }
 
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end,
+			unsigned flags)
 {
 	return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
 }
@@ -2126,7 +2143,7 @@
  * aggregate version in order to make the slab shrinker
  * faster
  */
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
 {
 	kvm->arch.n_used_mmu_pages += nr;
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
@@ -2226,13 +2243,6 @@
 {
 }
 
-static void nonpaging_update_pte(struct kvm_vcpu *vcpu,
-				 struct kvm_mmu_page *sp, u64 *spte,
-				 const void *pte)
-{
-	WARN_ON(1);
-}
-
 #define KVM_PAGE_ARRAY_NR 16
 
 struct kvm_mmu_pages {
@@ -3528,7 +3538,7 @@
  * - true: let the vcpu to access on the same address again.
  * - false: let the real page fault path to fix it.
  */
-static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
+static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int level,
 			    u32 error_code)
 {
 	struct kvm_shadow_walk_iterator iterator;
@@ -3548,7 +3558,7 @@
 	do {
 		u64 new_spte;
 
-		for_each_shadow_entry_lockless(vcpu, gva, iterator, spte)
+		for_each_shadow_entry_lockless(vcpu, cr2_or_gpa, iterator, spte)
 			if (!is_shadow_present_pte(spte) ||
 			    iterator.level < level)
 				break;
@@ -3626,7 +3636,7 @@
 
 	} while (true);
 
-	trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep,
+	trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep,
 			      spte, fault_handled);
 	walk_shadow_page_lockless_end(vcpu);
 
@@ -3634,10 +3644,11 @@
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable);
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+			 bool *writable);
 static int make_mmu_pages_available(struct kvm_vcpu *vcpu);
 
-static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
+static int nonpaging_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			 gfn_t gfn, bool prefault)
 {
 	int r;
@@ -3663,16 +3674,16 @@
 		gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1);
 	}
 
-	if (fast_page_fault(vcpu, v, level, error_code))
+	if (fast_page_fault(vcpu, gpa, level, error_code))
 		return RET_PF_RETRY;
 
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (try_async_pf(vcpu, prefault, gfn, v, &pfn, write, &map_writable))
+	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
 		return RET_PF_RETRY;
 
-	if (handle_abnormal_pfn(vcpu, v, gfn, pfn, ACC_ALL, &r))
+	if (handle_abnormal_pfn(vcpu, gpa, gfn, pfn, ACC_ALL, &r))
 		return r;
 
 	r = RET_PF_RETRY;
@@ -3683,7 +3694,7 @@
 		goto out_unlock;
 	if (likely(!force_pt_level))
 		transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
-	r = __direct_map(vcpu, v, write, map_writable, level, pfn,
+	r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
 			 prefault, false);
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
@@ -3981,7 +3992,7 @@
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
 
-static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				  u32 access, struct x86_exception *exception)
 {
 	if (exception)
@@ -3989,7 +4000,7 @@
 	return vaddr;
 }
 
-static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
+static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gpa_t vaddr,
 					 u32 access,
 					 struct x86_exception *exception)
 {
@@ -4149,13 +4160,14 @@
 	walk_shadow_page_lockless_end(vcpu);
 }
 
-static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
+static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa,
 				u32 error_code, bool prefault)
 {
-	gfn_t gfn = gva >> PAGE_SHIFT;
+	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int r;
 
-	pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
+	/* Note, paging is disabled, ergo gva == gpa. */
+	pgprintk("%s: gva %lx error %x\n", __func__, gpa, error_code);
 
 	if (page_fault_handle_page_track(vcpu, error_code, gfn))
 		return RET_PF_EMULATE;
@@ -4167,11 +4179,12 @@
 	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
 
 
-	return nonpaging_map(vcpu, gva & PAGE_MASK,
+	return nonpaging_map(vcpu, gpa & PAGE_MASK,
 			     error_code, gfn, prefault);
 }
 
-static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
+static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+				   gfn_t gfn)
 {
 	struct kvm_arch_async_pf arch;
 
@@ -4180,11 +4193,13 @@
 	arch.direct_map = vcpu->arch.mmu->direct_map;
 	arch.cr3 = vcpu->arch.mmu->get_cr3(vcpu);
 
-	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
+	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
+				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable)
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
+			 bool *writable)
 {
 	struct kvm_memory_slot *slot;
 	bool async;
@@ -4204,12 +4219,12 @@
 		return false; /* *pfn has correct page already */
 
 	if (!prefault && kvm_can_do_async_pf(vcpu)) {
-		trace_kvm_try_async_get_page(gva, gfn);
+		trace_kvm_try_async_get_page(cr2_or_gpa, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
-			trace_kvm_async_pf_doublefault(gva, gfn);
+			trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn);
 			kvm_make_request(KVM_REQ_APF_HALT, vcpu);
 			return true;
-		} else if (kvm_arch_setup_async_pf(vcpu, gva, gfn))
+		} else if (kvm_arch_setup_async_pf(vcpu, cr2_or_gpa, gfn))
 			return true;
 	}
 
@@ -4222,6 +4237,12 @@
 {
 	int r = 1;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit CR2 should be impossible on 32-bit KVM. */
+	if (WARN_ON_ONCE(fault_address >> 32))
+		return -EFAULT;
+#endif
+
 	vcpu->arch.l1tf_flush_l1d = true;
 	switch (vcpu->arch.apf.host_apf_reason) {
 	default:
@@ -4259,7 +4280,7 @@
 	return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num);
 }
 
-static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
+static int tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			  bool prefault)
 {
 	kvm_pfn_t pfn;
@@ -4328,7 +4349,6 @@
 	context->gva_to_gpa = nonpaging_gva_to_gpa;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
-	context->update_pte = nonpaging_update_pte;
 	context->root_level = 0;
 	context->shadow_root_level = PT32E_ROOT_LEVEL;
 	context->direct_map = true;
@@ -4564,7 +4584,7 @@
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | gbpages_bit_rsvd |
+			gbpages_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
@@ -4646,7 +4666,15 @@
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
-	bool uses_nx = context->nx ||
+	/*
+	 * KVM uses NX when TDP is disabled to handle a variety of scenarios,
+	 * notably for huge SPTEs if iTLB multi-hit mitigation is enabled and
+	 * to generate correct permissions for CR0.WP=0/CR4.SMEP=1/EFER.NX=0.
+	 * The iTLB multi-hit workaround can be toggled at any time, so assume
+	 * NX can be used by any non-nested shadow MMU to avoid having to reset
+	 * MMU contexts.  Note, KVM forces EFER.NX=1 when TDP is disabled.
+	 */
+	bool uses_nx = context->nx || !tdp_enabled ||
 		context->mmu_role.base.smep_andnot_wp;
 	struct rsvd_bits_validate *shadow_zero_check;
 	int i;
@@ -4907,7 +4935,6 @@
 	context->gva_to_gpa = paging64_gva_to_gpa;
 	context->sync_page = paging64_sync_page;
 	context->invlpg = paging64_invlpg;
-	context->update_pte = paging64_update_pte;
 	context->shadow_root_level = level;
 	context->direct_map = false;
 }
@@ -4936,7 +4963,6 @@
 	context->gva_to_gpa = paging32_gva_to_gpa;
 	context->sync_page = paging32_sync_page;
 	context->invlpg = paging32_invlpg;
-	context->update_pte = paging32_update_pte;
 	context->shadow_root_level = PT32E_ROOT_LEVEL;
 	context->direct_map = false;
 }
@@ -5011,7 +5037,6 @@
 	context->page_fault = tdp_page_fault;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
-	context->update_pte = nonpaging_update_pte;
 	context->shadow_root_level = kvm_x86_ops->get_tdp_level(vcpu);
 	context->direct_map = true;
 	context->set_cr3 = kvm_x86_ops->set_tdp_cr3;
@@ -5144,7 +5169,6 @@
 	context->gva_to_gpa = ept_gva_to_gpa;
 	context->sync_page = ept_sync_page;
 	context->invlpg = ept_invlpg;
-	context->update_pte = ept_update_pte;
 	context->root_level = PT64_ROOT_4LEVEL;
 	context->direct_map = false;
 	context->mmu_role.as_u64 = new_role.as_u64;
@@ -5284,19 +5308,6 @@
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unload);
 
-static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu_page *sp, u64 *spte,
-				  const void *new)
-{
-	if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
-		++vcpu->kvm->stat.mmu_pde_zapped;
-		return;
-        }
-
-	++vcpu->kvm->stat.mmu_pte_updated;
-	vcpu->arch.mmu->update_pte(vcpu, sp, spte, new);
-}
-
 static bool need_remote_flush(u64 old, u64 new)
 {
 	if (!is_shadow_present_pte(old))
@@ -5462,14 +5473,10 @@
 
 		local_flush = true;
 		while (npte--) {
-			u32 base_role = vcpu->arch.mmu->mmu_role.base.word;
-
 			entry = *spte;
 			mmu_page_zap_pte(vcpu->kvm, sp, spte);
-			if (gentry &&
-			      !((sp->role.word ^ base_role)
-			      & mmu_base_role_mask.word) && rmap_can_add(vcpu))
-				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
+			if (gentry && sp->role.level != PG_LEVEL_4K)
+				++vcpu->kvm->stat.mmu_pde_zapped;
 			if (need_remote_flush(entry, *spte))
 				remote_flush = true;
 			++spte;
@@ -5516,7 +5523,7 @@
 	return 0;
 }
 
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len)
 {
 	int r, emulation_type = 0;
@@ -5525,18 +5532,18 @@
 	/* With shadow page tables, fault_address contains a GVA or nGPA.  */
 	if (vcpu->arch.mmu->direct_map) {
 		vcpu->arch.gpa_available = true;
-		vcpu->arch.gpa_val = cr2;
+		vcpu->arch.gpa_val = cr2_or_gpa;
 	}
 
 	r = RET_PF_INVALID;
 	if (unlikely(error_code & PFERR_RSVD_MASK)) {
-		r = handle_mmio_page_fault(vcpu, cr2, direct);
+		r = handle_mmio_page_fault(vcpu, cr2_or_gpa, direct);
 		if (r == RET_PF_EMULATE)
 			goto emulate;
 	}
 
 	if (r == RET_PF_INVALID) {
-		r = vcpu->arch.mmu->page_fault(vcpu, cr2,
+		r = vcpu->arch.mmu->page_fault(vcpu, cr2_or_gpa,
 					       lower_32_bits(error_code),
 					       false);
 		WARN_ON(r == RET_PF_INVALID);
@@ -5556,7 +5563,7 @@
 	 */
 	if (vcpu->arch.mmu->direct_map &&
 	    (error_code & PFERR_NESTED_GUEST_PAGE) == PFERR_NESTED_GUEST_PAGE) {
-		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2));
+		kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(cr2_or_gpa));
 		return 1;
 	}
 
@@ -5571,7 +5578,7 @@
 	 * explicitly shadowing L1's page tables, i.e. unprotecting something
 	 * for L1 isn't going to magically fix whatever issue cause L2 to fail.
 	 */
-	if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu))
+	if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
 		emulation_type = EMULTYPE_ALLOW_RETRY;
 emulate:
 	/*
@@ -5586,7 +5593,7 @@
 			return 1;
 	}
 
-	return x86_emulate_instruction(vcpu, cr2, emulation_type, insn,
+	return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn,
 				       insn_len);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
@@ -6232,25 +6239,16 @@
 	u64 mask;
 
 	/*
-	 * Set the reserved bits and the present bit of an paging-structure
-	 * entry to generate page fault with PFER.RSV = 1.
+	 * Set a reserved PA bit in MMIO SPTEs to generate page faults with
+	 * PFEC.RSVD=1 on MMIO accesses.  64-bit PTEs (PAE, x86-64, and EPT
+	 * paging) support a maximum of 52 bits of PA, i.e. if the CPU supports
+	 * 52-bit physical addresses then there are no reserved PA bits in the
+	 * PTEs and so the reserved PA approach must be disabled.
 	 */
-
-	/*
-	 * Mask the uppermost physical address bit, which would be reserved as
-	 * long as the supported physical address width is less than 52.
-	 */
-	mask = 1ull << 51;
-
-	/* Set the present bit. */
-	mask |= 1ull;
-
-	/*
-	 * If reserved bit is not supported, clear the present bit to disable
-	 * mmio page fault.
-	 */
-	if (IS_ENABLED(CONFIG_X86_64) && shadow_phys_bits == 52)
-		mask &= ~1ull;
+	if (shadow_phys_bits < 52)
+		mask = BIT_ULL(51) | PT_PRESENT_MASK;
+	else
+		mask = 0;
 
 	kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
 }
@@ -6445,6 +6443,7 @@
 				cond_resched_lock(&kvm->mmu_lock);
 		}
 	}
+	kvm_mmu_commit_zap_page(kvm, &invalid_list);
 
 	spin_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, rcu_idx);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index d55674f..ea9945a 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -48,7 +48,7 @@
 	if (e < s)
 		return 0;
 
-	return ((1ULL << (e - s + 1)) - 1) << s;
+	return ((2ULL << (e - s)) - 1) << s;
 }
 
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask);
@@ -209,7 +209,7 @@
 void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 int kvm_mmu_post_init_vm(struct kvm *kvm);
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 7ca8831..ffcd96f 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -249,13 +249,13 @@
 
 TRACE_EVENT(
 	fast_page_fault,
-	TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
+	TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code,
 		 u64 *sptep, u64 old_spte, bool retry),
-	TP_ARGS(vcpu, gva, error_code, sptep, old_spte, retry),
+	TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry),
 
 	TP_STRUCT__entry(
 		__field(int, vcpu_id)
-		__field(gva_t, gva)
+		__field(gpa_t, cr2_or_gpa)
 		__field(u32, error_code)
 		__field(u64 *, sptep)
 		__field(u64, old_spte)
@@ -265,7 +265,7 @@
 
 	TP_fast_assign(
 		__entry->vcpu_id = vcpu->vcpu_id;
-		__entry->gva = gva;
+		__entry->cr2_or_gpa = cr2_or_gpa;
 		__entry->error_code = error_code;
 		__entry->sptep = sptep;
 		__entry->old_spte = old_spte;
@@ -273,9 +273,9 @@
 		__entry->retry = retry;
 	),
 
-	TP_printk("vcpu %d gva %lx error_code %s sptep %p old %#llx"
+	TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx"
 		  " new %llx spurious %d fixed %d", __entry->vcpu_id,
-		  __entry->gva, __print_flags(__entry->error_code, "|",
+		  __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|",
 		  kvm_mmu_trace_pferr_flags), __entry->sptep,
 		  __entry->old_spte, __entry->new_spte,
 		  __spte_satisfied(old_spte), __spte_satisfied(new_spte)
@@ -339,7 +339,7 @@
 		/* These depend on page entry type, so compute them now.  */
 		__field(bool, r)
 		__field(bool, x)
-		__field(u8, u)
+		__field(signed char, u)
 	),
 
 	TP_fast_assign(
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 25ce3ed..7f0059a 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -192,11 +192,15 @@
 		break;
 	case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000:
 		*seg = 1;
-		*unit = msr - MSR_MTRRfix16K_80000;
+		*unit = array_index_nospec(
+			msr - MSR_MTRRfix16K_80000,
+			MSR_MTRRfix16K_A0000 - MSR_MTRRfix16K_80000 + 1);
 		break;
 	case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000:
 		*seg = 2;
-		*unit = msr - MSR_MTRRfix4K_C0000;
+		*unit = array_index_nospec(
+			msr - MSR_MTRRfix4K_C0000,
+			MSR_MTRRfix4K_F8000 - MSR_MTRRfix4K_C0000 + 1);
 		break;
 	default:
 		return false;
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 97b21e7..d4a8ad6 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -33,7 +33,7 @@
 	#define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
 	#define PT_HAVE_ACCESSED_DIRTY(mmu) true
 	#ifdef CONFIG_X86_64
-	#define PT_MAX_FULL_LEVELS 4
+	#define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL
 	#define CMPXCHG cmpxchg
 	#else
 	#define CMPXCHG cmpxchg64
@@ -90,8 +90,8 @@
 	gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
 	pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
 	bool pte_writable[PT_MAX_FULL_LEVELS];
-	unsigned pt_access;
-	unsigned pte_access;
+	unsigned int pt_access[PT_MAX_FULL_LEVELS];
+	unsigned int pte_access;
 	gfn_t gfn;
 	struct x86_exception fault;
 };
@@ -220,7 +220,7 @@
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
-					     int write_fault)
+					     gpa_t addr, int write_fault)
 {
 	unsigned level, index;
 	pt_element_t pte, orig_pte;
@@ -245,7 +245,7 @@
 				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
 #if PTTYPE == PTTYPE_EPT
-			if (kvm_arch_write_log_dirty(vcpu))
+			if (kvm_arch_write_log_dirty(vcpu, addr))
 				return -EINVAL;
 #endif
 			pte |= PT_GUEST_DIRTY_MASK;
@@ -291,11 +291,11 @@
 }
 
 /*
- * Fetch a guest pte for a guest virtual address
+ * Fetch a guest pte for a guest virtual address, or for an L2's GPA.
  */
 static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-				    gva_t addr, u32 access)
+				    gpa_t addr, u32 access)
 {
 	int ret;
 	pt_element_t pte;
@@ -406,13 +406,15 @@
 		}
 
 		walker->ptes[walker->level - 1] = pte;
+
+		/* Convert to ACC_*_MASK flags for struct guest_walker.  */
+		walker->pt_access[walker->level - 1] = FNAME(gpte_access)(pt_access ^ walk_nx_mask);
 	} while (!is_last_gpte(mmu, walker->level, pte));
 
 	pte_pkey = FNAME(gpte_pkeys)(vcpu, pte);
 	accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;
 
 	/* Convert to ACC_*_MASK flags for struct guest_walker.  */
-	walker->pt_access = FNAME(gpte_access)(pt_access ^ walk_nx_mask);
 	walker->pte_access = FNAME(gpte_access)(pte_access ^ walk_nx_mask);
 	errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access);
 	if (unlikely(errcode))
@@ -442,7 +444,8 @@
 			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
-		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
+		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker,
+							addr, write_fault);
 		if (unlikely(ret < 0))
 			goto error;
 		else if (ret)
@@ -450,7 +453,8 @@
 	}
 
 	pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
-		 __func__, (u64)pte, walker->pte_access, walker->pt_access);
+		 __func__, (u64)pte, walker->pte_access,
+		 walker->pt_access[walker->level - 1]);
 	return 1;
 
 error:
@@ -496,7 +500,7 @@
 }
 
 static int FNAME(walk_addr)(struct guest_walker *walker,
-			    struct kvm_vcpu *vcpu, gva_t addr, u32 access)
+			    struct kvm_vcpu *vcpu, gpa_t addr, u32 access)
 {
 	return FNAME(walk_addr_generic)(walker, vcpu, vcpu->arch.mmu, addr,
 					access);
@@ -611,7 +615,7 @@
  * If the guest tries to write a write-protected page, we need to
  * emulate this operation, return 1 to indicate this case.
  */
-static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
+static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			 struct guest_walker *gw,
 			 int write_fault, int hlevel,
 			 kvm_pfn_t pfn, bool map_writable, bool prefault,
@@ -619,7 +623,7 @@
 {
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
-	unsigned direct_access, access = gw->pt_access;
+	unsigned int direct_access, access;
 	int top_level, ret;
 	gfn_t gfn, base_gfn;
 
@@ -651,6 +655,7 @@
 		sp = NULL;
 		if (!is_shadow_present_pte(*it.sptep)) {
 			table_gfn = gw->table_gfn[it.level - 2];
+			access = gw->pt_access[it.level - 2];
 			sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1,
 					      false, access);
 		}
@@ -765,7 +770,7 @@
  *  Returns: 1 if we need to emulate the instruction, 0 otherwise, or
  *           a negative value on error.
  */
-static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
+static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 			     bool prefault)
 {
 	int write_fault = error_code & PFERR_WRITE_MASK;
@@ -945,18 +950,19 @@
 	spin_unlock(&vcpu->kvm->mmu_lock);
 }
 
-static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
+/* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */
+static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gpa_t addr, u32 access,
 			       struct x86_exception *exception)
 {
 	struct guest_walker walker;
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
-	r = FNAME(walk_addr)(&walker, vcpu, vaddr, access);
+	r = FNAME(walk_addr)(&walker, vcpu, addr, access);
 
 	if (r) {
 		gpa = gfn_to_gpa(walker.gfn);
-		gpa |= vaddr & ~PAGE_MASK;
+		gpa |= addr & ~PAGE_MASK;
 	} else if (exception)
 		*exception = walker.fault;
 
@@ -964,7 +970,8 @@
 }
 
 #if PTTYPE != PTTYPE_EPT
-static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
+/* Note, gva_to_gpa_nested() is only used to translate L2 GVAs. */
+static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gpa_t vaddr,
 				      u32 access,
 				      struct x86_exception *exception)
 {
@@ -972,6 +979,11 @@
 	gpa_t gpa = UNMAPPED_GVA;
 	int r;
 
+#ifndef CONFIG_X86_64
+	/* A 64-bit GVA should be impossible on 32-bit KVM. */
+	WARN_ON_ONCE(vaddr >> 32);
+#endif
+
 	r = FNAME(walk_addr_nested)(&walker, vcpu, vaddr, access);
 
 	if (r) {
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 58265f7..3fc98af 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -2,6 +2,8 @@
 #ifndef __KVM_X86_PMU_H
 #define __KVM_X86_PMU_H
 
+#include <linux/nospec.h>
+
 #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu)
 #define pmu_to_vcpu(pmu)  (container_of((pmu), struct kvm_vcpu, arch.pmu))
 #define pmc_to_pmu(pmc)   (&(pmc)->vcpu->arch.pmu)
@@ -86,8 +88,12 @@
 static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr,
 					 u32 base)
 {
-	if (msr >= base && msr < base + pmu->nr_arch_gp_counters)
-		return &pmu->gp_counters[msr - base];
+	if (msr >= base && msr < base + pmu->nr_arch_gp_counters) {
+		u32 index = array_index_nospec(msr - base,
+					       pmu->nr_arch_gp_counters);
+
+		return &pmu->gp_counters[index];
+	}
 
 	return NULL;
 }
@@ -97,8 +103,12 @@
 {
 	int base = MSR_CORE_PERF_FIXED_CTR0;
 
-	if (msr >= base && msr < base + pmu->nr_arch_fixed_counters)
-		return &pmu->fixed_counters[msr - base];
+	if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) {
+		u32 index = array_index_nospec(msr - base,
+					       pmu->nr_arch_fixed_counters);
+
+		return &pmu->fixed_counters[index];
+	}
 
 	return NULL;
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c5673bd..425444d 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -516,6 +516,9 @@
 	c->intercept_dr = h->intercept_dr | g->intercept_dr;
 	c->intercept_exceptions = h->intercept_exceptions | g->intercept_exceptions;
 	c->intercept = h->intercept | g->intercept;
+
+	c->intercept |= (1ULL << INTERCEPT_VMLOAD);
+	c->intercept |= (1ULL << INTERCEPT_VMSAVE);
 }
 
 static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm)
@@ -787,9 +790,6 @@
 		if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
 			return 0;
 	} else {
-		if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE)
-			pr_err("%s: ip 0x%lx next 0x%llx\n",
-			       __func__, kvm_rip_read(vcpu), svm->next_rip);
 		kvm_rip_write(vcpu, svm->next_rip);
 	}
 	svm_set_interrupt_shadow(vcpu, 0);
@@ -892,6 +892,11 @@
 		return 0;
 	}
 
+	if (sev_active()) {
+		pr_info("KVM is unsupported when running as an SEV guest\n");
+		return 0;
+	}
+
 	return 1;
 }
 
@@ -998,33 +1003,32 @@
 static int svm_cpu_init(int cpu)
 {
 	struct svm_cpu_data *sd;
-	int r;
 
 	sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
 	if (!sd)
 		return -ENOMEM;
 	sd->cpu = cpu;
-	r = -ENOMEM;
 	sd->save_area = alloc_page(GFP_KERNEL);
 	if (!sd->save_area)
-		goto err_1;
+		goto free_cpu_data;
 
 	if (svm_sev_enabled()) {
-		r = -ENOMEM;
 		sd->sev_vmcbs = kmalloc_array(max_sev_asid + 1,
 					      sizeof(void *),
 					      GFP_KERNEL);
 		if (!sd->sev_vmcbs)
-			goto err_1;
+			goto free_save_area;
 	}
 
 	per_cpu(svm_data, cpu) = sd;
 
 	return 0;
 
-err_1:
+free_save_area:
+	__free_page(sd->save_area);
+free_cpu_data:
 	kfree(sd);
-	return r;
+	return -ENOMEM;
 
 }
 
@@ -1298,6 +1302,47 @@
 	}
 }
 
+/*
+ * The default MMIO mask is a single bit (excluding the present bit),
+ * which could conflict with the memory encryption bit. Check for
+ * memory encryption support and override the default MMIO mask if
+ * memory encryption is enabled.
+ */
+static __init void svm_adjust_mmio_mask(void)
+{
+	unsigned int enc_bit, mask_bit;
+	u64 msr, mask;
+
+	/* If there is no memory encryption support, use existing mask */
+	if (cpuid_eax(0x80000000) < 0x8000001f)
+		return;
+
+	/* If memory encryption is not enabled, use existing mask */
+	rdmsrl(MSR_K8_SYSCFG, msr);
+	if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
+		return;
+
+	enc_bit = cpuid_ebx(0x8000001f) & 0x3f;
+	mask_bit = boot_cpu_data.x86_phys_bits;
+
+	/* Increment the mask bit if it is the same as the encryption bit */
+	if (enc_bit == mask_bit)
+		mask_bit++;
+
+	/*
+	 * If the mask bit location is below 52, then some bits above the
+	 * physical addressing limit will always be reserved, so use the
+	 * rsvd_bits() function to generate the mask. This mask, along with
+	 * the present bit, will be used to generate a page fault with
+	 * PFER.RSV = 1.
+	 *
+	 * If the mask bit location is 52 (or above), then clear the mask.
+	 */
+	mask = (mask_bit < 52) ? rsvd_bits(mask_bit, 51) | PT_PRESENT_MASK : 0;
+
+	kvm_mmu_set_mmio_spte_mask(mask, mask, PT_WRITABLE_MASK | PT_USER_MASK);
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -1352,6 +1397,8 @@
 		}
 	}
 
+	svm_adjust_mmio_mask();
+
 	for_each_possible_cpu(cpu) {
 		r = svm_cpu_init(cpu);
 		if (r)
@@ -1399,12 +1446,7 @@
 		}
 	}
 
-	if (vgif) {
-		if (!boot_cpu_has(X86_FEATURE_VGIF))
-			vgif = false;
-		else
-			pr_info("Virtual GIF supported\n");
-	}
+	vgif = false; /* Disabled for CVE-2021-3653 */
 
 	return 0;
 
@@ -1739,7 +1781,7 @@
 
 	for_each_possible_cpu(cpu) {
 		sd = per_cpu(svm_data, cpu);
-		sd->sev_vmcbs[pos] = NULL;
+		sd->sev_vmcbs[asid] = NULL;
 	}
 }
 
@@ -1750,9 +1792,25 @@
 	__sev_asid_free(sev->asid);
 }
 
-static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
+static void sev_decommission(unsigned int handle)
 {
 	struct sev_data_decommission *decommission;
+
+	if (!handle)
+		return;
+
+	decommission = kzalloc(sizeof(*decommission), GFP_KERNEL);
+	if (!decommission)
+		return;
+
+	decommission->handle = handle;
+	sev_guest_decommission(decommission, NULL);
+
+	kfree(decommission);
+}
+
+static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
+{
 	struct sev_data_deactivate *data;
 
 	if (!handle)
@@ -1770,15 +1828,7 @@
 	sev_guest_df_flush(NULL);
 	kfree(data);
 
-	decommission = kzalloc(sizeof(*decommission), GFP_KERNEL);
-	if (!decommission)
-		return;
-
-	/* decommission handle */
-	decommission->handle = handle;
-	sev_guest_decommission(decommission, NULL);
-
-	kfree(decommission);
+	sev_decommission(handle);
 }
 
 static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
@@ -1791,6 +1841,8 @@
 	struct page **pages;
 	unsigned long first, last;
 
+	lockdep_assert_held(&kvm->lock);
+
 	if (ulen == 0 || uaddr + ulen < uaddr)
 		return NULL;
 
@@ -1818,7 +1870,7 @@
 		return NULL;
 
 	/* Pin the user virtual address. */
-	npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
+	npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
 	if (npinned != npages) {
 		pr_err("SEV: Failure locking %lu pages.\n", npages);
 		goto err;
@@ -1883,6 +1935,10 @@
 	struct kvm_svm *kvm_svm = __vmalloc(sizeof(struct kvm_svm),
 					    GFP_KERNEL_ACCOUNT | __GFP_ZERO,
 					    PAGE_KERNEL);
+
+	if (!kvm_svm)
+		return NULL;
+
 	return &kvm_svm->kvm;
 }
 
@@ -1910,6 +1966,7 @@
 		list_for_each_safe(pos, q, head) {
 			__unregister_enc_region_locked(kvm,
 				list_entry(pos, struct enc_region, list));
+			cond_resched();
 		}
 	}
 
@@ -3191,8 +3248,8 @@
 			return NESTED_EXIT_HOST;
 		break;
 	case SVM_EXIT_EXCP_BASE + PF_VECTOR:
-		/* When we're shadowing, trap PFs, but not async PF */
-		if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0)
+		/* Trap async PF even if not shadowing */
+		if (!npt_enabled || svm->vcpu.arch.apf.host_apf_reason)
 			return NESTED_EXIT_HOST;
 		break;
 	default:
@@ -3281,7 +3338,7 @@
 	dst->iopm_base_pa         = from->iopm_base_pa;
 	dst->msrpm_base_pa        = from->msrpm_base_pa;
 	dst->tsc_offset           = from->tsc_offset;
-	dst->asid                 = from->asid;
+	/* asid not copied, it is handled manually for svm->vmcb.  */
 	dst->tlb_ctl              = from->tlb_ctl;
 	dst->int_ctl              = from->int_ctl;
 	dst->int_vector           = from->int_vector;
@@ -3548,7 +3605,13 @@
 	svm->nested.intercept            = nested_vmcb->control.intercept;
 
 	svm_flush_tlb(&svm->vcpu, true);
-	svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
+
+	svm->vmcb->control.int_ctl &=
+			V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK;
+
+	svm->vmcb->control.int_ctl |= nested_vmcb->control.int_ctl &
+			(V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK);
+
 	if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
 		svm->vcpu.arch.hflags |= HF_VINTR_MASK;
 	else
@@ -3924,6 +3987,12 @@
 	return 1;
 }
 
+static int invd_interception(struct vcpu_svm *svm)
+{
+	/* Treat an INVD instruction as a NOP and just skip it. */
+	return kvm_skip_emulated_instruction(&svm->vcpu);
+}
+
 static int invlpg_interception(struct vcpu_svm *svm)
 {
 	if (!static_cpu_has(X86_FEATURE_DECODEASSISTS))
@@ -4001,7 +4070,7 @@
 	err = 0;
 	if (cr >= 16) { /* mov to cr */
 		cr -= 16;
-		val = kvm_register_read(&svm->vcpu, reg);
+		val = kvm_register_readl(&svm->vcpu, reg);
 		switch (cr) {
 		case 0:
 			if (!check_selective_cr0_intercepted(svm, val))
@@ -4046,7 +4115,7 @@
 			kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 			return 1;
 		}
-		kvm_register_write(&svm->vcpu, reg, val);
+		kvm_register_writel(&svm->vcpu, reg, val);
 	}
 	return kvm_complete_insn_gp(&svm->vcpu, err);
 }
@@ -4076,13 +4145,13 @@
 	if (dr >= 16) { /* mov to DRn */
 		if (!kvm_require_dr(&svm->vcpu, dr - 16))
 			return 1;
-		val = kvm_register_read(&svm->vcpu, reg);
+		val = kvm_register_readl(&svm->vcpu, reg);
 		kvm_set_dr(&svm->vcpu, dr - 16, val);
 	} else {
 		if (!kvm_require_dr(&svm->vcpu, dr))
 			return 1;
 		kvm_get_dr(&svm->vcpu, dr, &val);
-		kvm_register_write(&svm->vcpu, reg, val);
+		kvm_register_writel(&svm->vcpu, reg, val);
 	}
 
 	return kvm_skip_emulated_instruction(&svm->vcpu);
@@ -4184,8 +4253,7 @@
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD))
+		    !guest_has_spec_ctrl_msr(vcpu))
 			return 1;
 
 		msr_info->data = svm->spec_ctrl;
@@ -4269,16 +4337,13 @@
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD))
+		    !guest_has_spec_ctrl_msr(vcpu))
 			return 1;
 
-		/* The STIBP bit doesn't fault even if it's not advertised */
-		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
+		if (kvm_spec_ctrl_test_value(data))
 			return 1;
 
 		svm->spec_ctrl = data;
-
 		if (!data)
 			break;
 
@@ -4297,18 +4362,17 @@
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB))
+		    !guest_has_pred_cmd_msr(vcpu))
 			return 1;
 
 		if (data & ~PRED_CMD_IBPB)
 			return 1;
-
+		if (!boot_cpu_has(X86_FEATURE_IBPB))
+			return 1;
 		if (!data)
 			break;
 
 		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
-		if (is_guest_mode(vcpu))
-			break;
 		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
@@ -4776,7 +4840,7 @@
 	[SVM_EXIT_RDPMC]			= rdpmc_interception,
 	[SVM_EXIT_CPUID]			= cpuid_interception,
 	[SVM_EXIT_IRET]                         = iret_interception,
-	[SVM_EXIT_INVD]                         = emulate_on_interception,
+	[SVM_EXIT_INVD]                         = invd_interception,
 	[SVM_EXIT_PAUSE]			= pause_interception,
 	[SVM_EXIT_HLT]				= halt_interception,
 	[SVM_EXIT_INVLPG]			= invlpg_interception,
@@ -5141,8 +5205,11 @@
 	return;
 }
 
-static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
+static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 {
+	if (!vcpu->arch.apicv_active)
+		return -1;
+
 	kvm_lapic_set_irr(vec, vcpu->arch.apic);
 	smp_mb__after_atomic();
 
@@ -5154,6 +5221,8 @@
 		put_cpu();
 	} else
 		kvm_vcpu_wake_up(vcpu);
+
+	return 0;
 }
 
 static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
@@ -5329,6 +5398,7 @@
 			 * - Tell IOMMU to use legacy mode for this interrupt.
 			 * - Retrieve ga_tag of prior interrupt remapping data.
 			 */
+			pi.prev_ga_tag = 0;
 			pi.is_guest_mode = false;
 			ret = irq_set_vcpu_affinity(host_irq, &pi);
 
@@ -5986,6 +6056,11 @@
 	return true;
 }
 
+static bool svm_pku_supported(void)
+{
+	return false;
+}
+
 #define PRE_EX(exit)  { .exit_code = (exit), \
 			.stage = X86_ICPT_PRE_EXCEPT, }
 #define POST_EX(exit) { .exit_code = (exit), \
@@ -6413,8 +6488,10 @@
 
 	/* Bind ASID to this guest */
 	ret = sev_bind_asid(kvm, start->handle, error);
-	if (ret)
+	if (ret) {
+		sev_decommission(start->handle);
 		goto e_free_session;
+	}
 
 	/* return handle to userspace */
 	params.handle = start->handle;
@@ -7031,12 +7108,20 @@
 	if (!region)
 		return -ENOMEM;
 
+	mutex_lock(&kvm->lock);
 	region->pages = sev_pin_memory(kvm, range->addr, range->size, &region->npages, 1);
 	if (!region->pages) {
 		ret = -ENOMEM;
+		mutex_unlock(&kvm->lock);
 		goto e_free;
 	}
 
+	region->uaddr = range->addr;
+	region->size = range->size;
+
+	list_add_tail(&region->list, &sev->regions_list);
+	mutex_unlock(&kvm->lock);
+
 	/*
 	 * The guest may change the memory encryption attribute from C=0 -> C=1
 	 * or vice versa for this memory range. Lets make sure caches are
@@ -7045,13 +7130,6 @@
 	 */
 	sev_clflush_pages(region->pages, region->npages);
 
-	region->uaddr = range->addr;
-	region->size = range->size;
-
-	mutex_lock(&kvm->lock);
-	list_add_tail(&region->list, &sev->regions_list);
-	mutex_unlock(&kvm->lock);
-
 	return ret;
 
 e_free:
@@ -7278,6 +7356,7 @@
 	.xsaves_supported = svm_xsaves_supported,
 	.umip_emulated = svm_umip_emulated,
 	.pt_supported = svm_pt_supported,
+	.pku_supported = svm_pku_supported,
 
 	.set_supported_cpuid = svm_set_supported_cpuid,
 
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 7c741a0..5fed9c4 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1483,16 +1483,16 @@
 	TP_ARGS(msg, err),
 
 	TP_STRUCT__entry(
-		__field(const char *, msg)
+		__string(msg, msg)
 		__field(u32, err)
 	),
 
 	TP_fast_assign(
-		__entry->msg = msg;
+		__assign_str(msg, msg);
 		__entry->err = err;
 	),
 
-	TP_printk("%s%s", __entry->msg, !__entry->err ? "" :
+	TP_printk("%s%s", __get_str(msg), !__entry->err ? "" :
 		__print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS))
 );
 
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 7aa6971..f486e26 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -12,6 +12,7 @@
 extern bool __read_mostly enable_unrestricted_guest;
 extern bool __read_mostly enable_ept_ad_bits;
 extern bool __read_mostly enable_pml;
+extern bool __read_mostly enable_apicv;
 extern int __read_mostly pt_mode;
 
 #define PT_MODE_SYSTEM		0
@@ -145,6 +146,11 @@
 		SECONDARY_EXEC_DESC;
 }
 
+static inline bool vmx_pku_supported(void)
+{
+	return boot_cpu_has(X86_FEATURE_PKU);
+}
+
 static inline bool cpu_has_vmx_rdtscp(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0e7c930..3041015 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -223,7 +223,7 @@
 		return;
 
 	kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true);
-	vmx->nested.hv_evmcs_vmptr = -1ull;
+	vmx->nested.hv_evmcs_vmptr = 0;
 	vmx->nested.hv_evmcs = NULL;
 }
 
@@ -302,7 +302,7 @@
 	cpu = get_cpu();
 	prev = vmx->loaded_vmcs;
 	vmx->loaded_vmcs = vmcs;
-	vmx_vcpu_load_vmcs(vcpu, cpu);
+	vmx_vcpu_load_vmcs(vcpu, cpu, prev);
 	vmx_sync_vmcs_host_state(vmx, prev);
 	put_cpu();
 
@@ -1828,7 +1828,8 @@
 	if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa))
 		return 1;
 
-	if (unlikely(evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) {
+	if (unlikely(!vmx->nested.hv_evmcs ||
+		     evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) {
 		if (!vmx->nested.hv_evmcs)
 			vmx->nested.current_vmptr = -1ull;
 
@@ -2056,12 +2057,11 @@
 			 ~PIN_BASED_VMX_PREEMPTION_TIMER);
 
 	/* Posted interrupts setting is only taken from vmcs12.  */
-	if (nested_cpu_has_posted_intr(vmcs12)) {
+	vmx->nested.pi_pending = false;
+	if (nested_cpu_has_posted_intr(vmcs12))
 		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
-		vmx->nested.pi_pending = false;
-	} else {
+	else
 		exec_control &= ~PIN_BASED_POSTED_INTR;
-	}
 	pin_controls_set(vmx, exec_control);
 
 	/*
@@ -2230,6 +2230,8 @@
 		vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
 		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
 		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
+
+		vmx->segment_cache.bitmask = 0;
 	}
 
 	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
@@ -2418,6 +2420,16 @@
 				entry_failure_code))
 		return -EINVAL;
 
+	/*
+	 * Immediately write vmcs02.GUEST_CR3.  It will be propagated to vmcs12
+	 * on nested VM-Exit, which can occur without actually running L2 and
+	 * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with
+	 * vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the
+	 * transition to HLT instead of running L2.
+	 */
+	if (enable_ept)
+		vmcs_writel(GUEST_CR3, vmcs12->guest_cr3);
+
 	/* Late preparation of GUEST_PDPTRs now that EFER and CRs are set. */
 	if (load_guest_pdptrs_vmcs12 && nested_cpu_has_ept(vmcs12) &&
 	    is_pae_paging(vcpu)) {
@@ -3083,8 +3095,10 @@
 	prepare_vmcs02_early(vmx, vmcs12);
 
 	if (from_vmentry) {
-		if (unlikely(!nested_get_vmcs12_pages(vcpu)))
+		if (unlikely(!nested_get_vmcs12_pages(vcpu))) {
+			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 			return NVMX_VMENTRY_KVM_INTERNAL_ERROR;
+		}
 
 		if (nested_vmx_check_vmentry_hw(vcpu)) {
 			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
@@ -3449,7 +3463,7 @@
 	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
 }
 
-static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
+static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qual;
@@ -3496,8 +3510,7 @@
 		return 0;
 	}
 
-	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
-	    nested_exit_on_intr(vcpu)) {
+	if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) {
 		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
@@ -4147,17 +4160,8 @@
 	vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	if (likely(!vmx->fail)) {
-		/*
-		 * TODO: SDM says that with acknowledge interrupt on
-		 * exit, bit 31 of the VM-exit interrupt information
-		 * (valid interrupt) is always set to 1 on
-		 * EXIT_REASON_EXTERNAL_INTERRUPT, so we shouldn't
-		 * need kvm_cpu_has_interrupt().  See the commit
-		 * message for details.
-		 */
-		if (nested_exit_intr_ack_set(vcpu) &&
-		    exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
-		    kvm_cpu_has_interrupt(vcpu)) {
+		if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+		    nested_exit_intr_ack_set(vcpu)) {
 			int irq = kvm_cpu_get_interrupt(vcpu);
 			WARN_ON(irq < 0);
 			vmcs12->vm_exit_intr_info = irq |
@@ -4599,32 +4603,28 @@
 {
 	unsigned long field;
 	u64 field_value;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
 	int len;
 	gva_t gva = 0;
-	struct vmcs12 *vmcs12;
+	struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu)
+						    : get_vmcs12(vcpu);
 	struct x86_exception e;
 	short offset;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (to_vmx(vcpu)->nested.current_vmptr == -1ull)
+	/*
+	 * In VMX non-root operation, when the VMCS-link pointer is -1ull,
+	 * any VMREAD sets the ALU flags for VMfailInvalid.
+	 */
+	if (vmx->nested.current_vmptr == -1ull ||
+	    (is_guest_mode(vcpu) &&
+	     get_vmcs12(vcpu)->vmcs_link_pointer == -1ull))
 		return nested_vmx_failInvalid(vcpu);
 
-	if (!is_guest_mode(vcpu))
-		vmcs12 = get_vmcs12(vcpu);
-	else {
-		/*
-		 * When vmcs->vmcs_link_pointer is -1ull, any VMREAD
-		 * to shadowed-field sets the ALU flags for VMfailInvalid.
-		 */
-		if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
-			return nested_vmx_failInvalid(vcpu);
-		vmcs12 = get_shadow_vmcs12(vcpu);
-	}
-
 	/* Decode instruction info and find the field to read */
 	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
 
@@ -4653,8 +4653,10 @@
 				vmx_instruction_info, true, len, &gva))
 			return 1;
 		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
-		if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e))
+		if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e)) {
 			kvm_inject_page_fault(vcpu, &e);
+			return 1;
+		}
 	}
 
 	return nested_vmx_succeed(vcpu);
@@ -4701,13 +4703,20 @@
 	 */
 	u64 field_value = 0;
 	struct x86_exception e;
-	struct vmcs12 *vmcs12;
+	struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu)
+						    : get_vmcs12(vcpu);
 	short offset;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (vmx->nested.current_vmptr == -1ull)
+	/*
+	 * In VMX non-root operation, when the VMCS-link pointer is -1ull,
+	 * any VMWRITE sets the ALU flags for VMfailInvalid.
+	 */
+	if (vmx->nested.current_vmptr == -1ull ||
+	    (is_guest_mode(vcpu) &&
+	     get_vmcs12(vcpu)->vmcs_link_pointer == -1ull))
 		return nested_vmx_failInvalid(vcpu);
 
 	if (vmx_instruction_info & (1u << 10))
@@ -4726,6 +4735,12 @@
 
 
 	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+
+	offset = vmcs_field_to_offset(field);
+	if (offset < 0)
+		return nested_vmx_failValid(vcpu,
+			VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
 	/*
 	 * If the vCPU supports "VMWRITE to any supported field in the
 	 * VMCS," then the "read-only" fields are actually read/write.
@@ -4735,29 +4750,12 @@
 		return nested_vmx_failValid(vcpu,
 			VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
 
-	if (!is_guest_mode(vcpu)) {
-		vmcs12 = get_vmcs12(vcpu);
-
-		/*
-		 * Ensure vmcs12 is up-to-date before any VMWRITE that dirties
-		 * vmcs12, else we may crush a field or consume a stale value.
-		 */
-		if (!is_shadow_field_rw(field))
-			copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
-	} else {
-		/*
-		 * When vmcs->vmcs_link_pointer is -1ull, any VMWRITE
-		 * to shadowed-field sets the ALU flags for VMfailInvalid.
-		 */
-		if (get_vmcs12(vcpu)->vmcs_link_pointer == -1ull)
-			return nested_vmx_failInvalid(vcpu);
-		vmcs12 = get_shadow_vmcs12(vcpu);
-	}
-
-	offset = vmcs_field_to_offset(field);
-	if (offset < 0)
-		return nested_vmx_failValid(vcpu,
-			VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+	/*
+	 * Ensure vmcs12 is up-to-date before any VMWRITE that dirties
+	 * vmcs12, else we may crush a field or consume a stale value.
+	 */
+	if (!is_guest_mode(vcpu) && !is_shadow_field_rw(field))
+		copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
 
 	/*
 	 * Some Intel CPUs intentionally drop the reserved bits of the AR byte
@@ -5100,7 +5098,7 @@
 	}
 
 	vmcs12 = get_vmcs12(vcpu);
-	if ((vmcs12->vm_function_control & (1 << function)) == 0)
+	if (!(vmcs12->vm_function_control & BIT_ULL(function)))
 		goto fail;
 
 	switch (function) {
@@ -5120,24 +5118,17 @@
 	return 1;
 }
 
-
-static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
-				       struct vmcs12 *vmcs12)
+/*
+ * Return true if an IO instruction with the specified port and size should cause
+ * a VM-exit into L1.
+ */
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+				 int size)
 {
-	unsigned long exit_qualification;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	gpa_t bitmap, last_bitmap;
-	unsigned int port;
-	int size;
 	u8 b;
 
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
-		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	port = exit_qualification >> 16;
-	size = (exit_qualification & 7) + 1;
-
 	last_bitmap = (gpa_t)-1;
 	b = -1;
 
@@ -5164,6 +5155,24 @@
 	return false;
 }
 
+static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	unsigned long exit_qualification;
+	unsigned short port;
+	int size;
+
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
+
+	return nested_vmx_check_io_bitmaps(vcpu, port, size);
+}
+
 /*
  * Return 1 if we should exit from L2 to L1 to handle an MSR access access,
  * rather than handle it ourselves in L0. I.e., check whether L1 expressed
@@ -5298,7 +5307,7 @@
 
 	/* Decode instruction info and find the field to access */
 	vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-	field = kvm_register_read(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+	field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
 
 	/* Out-of-range fields always cause a VM exit from L2 to L1 */
 	if (field >> 15)
@@ -5351,7 +5360,7 @@
 				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
 				KVM_ISA_VMX);
 
-	switch (exit_reason) {
+	switch ((u16)exit_reason) {
 	case EXIT_REASON_EXCEPTION_NMI:
 		if (is_nmi(intr_info))
 			return false;
@@ -5569,11 +5578,14 @@
 	if (is_guest_mode(vcpu)) {
 		sync_vmcs02_to_vmcs12(vcpu, vmcs12);
 		sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
-	} else if (!vmx->nested.need_vmcs12_to_shadow_sync) {
-		if (vmx->nested.hv_evmcs)
-			copy_enlightened_to_vmcs12(vmx);
-		else if (enable_shadow_vmcs)
-			copy_shadow_to_vmcs12(vmx);
+	} else  {
+		copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu));
+		if (!vmx->nested.need_vmcs12_to_shadow_sync) {
+			if (vmx->nested.hv_evmcs)
+				copy_enlightened_to_vmcs12(vmx);
+			else if (enable_shadow_vmcs)
+				copy_shadow_to_vmcs12(vmx);
+		}
 	}
 
 	BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE);
@@ -5784,8 +5796,7 @@
  * bit in the high half is on if the corresponding bit in the control field
  * may be on. See also vmx_control_verify().
  */
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv)
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 {
 	/*
 	 * Note that as a general rule, the high half of the MSRs (bits in
@@ -5812,7 +5823,7 @@
 		PIN_BASED_EXT_INTR_MASK |
 		PIN_BASED_NMI_EXITING |
 		PIN_BASED_VIRTUAL_NMIS |
-		(apicv ? PIN_BASED_POSTED_INTR : 0);
+		(enable_apicv ? PIN_BASED_POSTED_INTR : 0);
 	msrs->pinbased_ctls_high |=
 		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
 		PIN_BASED_VMX_PREEMPTION_TIMER;
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 6280f33..b8521c4 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -17,8 +17,7 @@
 };
 
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv);
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_vcpu_setup(void);
@@ -33,6 +32,8 @@
 int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata);
 int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 			u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+				 int size);
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/vmx/ops.h b/arch/x86/kvm/vmx/ops.h
index 45eaede..19717d0 100644
--- a/arch/x86/kvm/vmx/ops.h
+++ b/arch/x86/kvm/vmx/ops.h
@@ -13,6 +13,8 @@
 #define __ex(x) __kvm_handle_fault_on_reboot(x)
 
 asmlinkage void vmread_error(unsigned long field, bool fault);
+__attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field,
+							 bool fault);
 void vmwrite_error(unsigned long field, unsigned long value);
 void vmclear_error(struct vmcs *vmcs, u64 phys_addr);
 void vmptrld_error(struct vmcs *vmcs, u64 phys_addr);
@@ -70,15 +72,28 @@
 	asm volatile("1: vmread %2, %1\n\t"
 		     ".byte 0x3e\n\t" /* branch taken hint */
 		     "ja 3f\n\t"
-		     "mov %2, %%" _ASM_ARG1 "\n\t"
-		     "xor %%" _ASM_ARG2 ", %%" _ASM_ARG2 "\n\t"
-		     "2: call vmread_error\n\t"
-		     "xor %k1, %k1\n\t"
+
+		     /*
+		      * VMREAD failed.  Push '0' for @fault, push the failing
+		      * @field, and bounce through the trampoline to preserve
+		      * volatile registers.
+		      */
+		     "push $0\n\t"
+		     "push %2\n\t"
+		     "2:call vmread_error_trampoline\n\t"
+
+		     /*
+		      * Unwind the stack.  Note, the trampoline zeros out the
+		      * memory for @fault so that the result is '0' on error.
+		      */
+		     "pop %2\n\t"
+		     "pop %1\n\t"
 		     "3:\n\t"
 
+		     /* VMREAD faulted.  As above, except push '1' for @fault. */
 		     ".pushsection .fixup, \"ax\"\n\t"
-		     "4: mov %2, %%" _ASM_ARG1 "\n\t"
-		     "mov $1, %%" _ASM_ARG2 "\n\t"
+		     "4: push $1\n\t"
+		     "push %2\n\t"
 		     "jmp 2b\n\t"
 		     ".popsection\n\t"
 		     _ASM_EXTABLE(1b, 4b)
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 3e9c059..181e352 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -26,7 +26,7 @@
 	[4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
 	[5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
 	[6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
-	[7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES },
+	[7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES },
 };
 
 /* mapping between fixed pmc index and intel_arch_events array */
@@ -84,10 +84,14 @@
 
 static unsigned intel_find_fixed_event(int idx)
 {
-	if (idx >= ARRAY_SIZE(fixed_pmc_events))
+	u32 event;
+	size_t size = ARRAY_SIZE(fixed_pmc_events);
+
+	if (idx >= size)
 		return PERF_COUNT_HW_MAX;
 
-	return intel_arch_events[fixed_pmc_events[idx]].event_type;
+	event = fixed_pmc_events[array_index_nospec(idx, size)];
+	return intel_arch_events[event].event_type;
 }
 
 /* check if a PMC is enabled by comparing it with globl_ctrl bits. */
@@ -128,16 +132,20 @@
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	bool fixed = idx & (1u << 30);
 	struct kvm_pmc *counters;
+	unsigned int num_counters;
 
 	idx &= ~(3u << 30);
-	if (!fixed && idx >= pmu->nr_arch_gp_counters)
+	if (fixed) {
+		counters = pmu->fixed_counters;
+		num_counters = pmu->nr_arch_fixed_counters;
+	} else {
+		counters = pmu->gp_counters;
+		num_counters = pmu->nr_arch_gp_counters;
+	}
+	if (idx >= num_counters)
 		return NULL;
-	if (fixed && idx >= pmu->nr_arch_fixed_counters)
-		return NULL;
-	counters = fixed ? pmu->fixed_counters : pmu->gp_counters;
 	*mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP];
-
-	return &counters[idx];
+	return &counters[array_index_nospec(idx, num_counters)];
 }
 
 static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
@@ -288,7 +296,9 @@
 
 	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
 					 x86_pmu.num_counters_gp);
+	eax.split.bit_width = min_t(int, eax.split.bit_width, x86_pmu.bit_width_gp);
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
+	eax.split.mask_length = min_t(int, eax.split.mask_length, x86_pmu.events_mask_len);
 	pmu->available_event_types = ~entry->ebx &
 					((1ull << eax.split.mask_length) - 1);
 
@@ -298,6 +308,8 @@
 		pmu->nr_arch_fixed_counters =
 			min_t(int, edx.split.num_counters_fixed,
 			      x86_pmu.num_counters_fixed);
+		edx.split.bit_width_fixed = min_t(int,
+			edx.split.bit_width_fixed, x86_pmu.bit_width_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 751a384..ca4252f 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -86,6 +86,9 @@
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
 
+	/* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */
+	or $1, %_ASM_AX
+
 	pop %_ASM_AX
 .Lvmexit_skip_rsb:
 #endif
@@ -234,3 +237,61 @@
 2:	mov $1, %eax
 	jmp 1b
 ENDPROC(__vmx_vcpu_run)
+
+/**
+ * vmread_error_trampoline - Trampoline from inline asm to vmread_error()
+ * @field:	VMCS field encoding that failed
+ * @fault:	%true if the VMREAD faulted, %false if it failed
+
+ * Save and restore volatile registers across a call to vmread_error().  Note,
+ * all parameters are passed on the stack.
+ */
+ENTRY(vmread_error_trampoline)
+	push %_ASM_BP
+	mov  %_ASM_SP, %_ASM_BP
+
+	push %_ASM_AX
+	push %_ASM_CX
+	push %_ASM_DX
+#ifdef CONFIG_X86_64
+	push %rdi
+	push %rsi
+	push %r8
+	push %r9
+	push %r10
+	push %r11
+#endif
+#ifdef CONFIG_X86_64
+	/* Load @field and @fault to arg1 and arg2 respectively. */
+	mov 3*WORD_SIZE(%rbp), %_ASM_ARG2
+	mov 2*WORD_SIZE(%rbp), %_ASM_ARG1
+#else
+	/* Parameters are passed on the stack for 32-bit (see asmlinkage). */
+	push 3*WORD_SIZE(%ebp)
+	push 2*WORD_SIZE(%ebp)
+#endif
+
+	call vmread_error
+
+#ifndef CONFIG_X86_64
+	add $8, %esp
+#endif
+
+	/* Zero out @fault, which will be popped into the result register. */
+	_ASM_MOV $0, 3*WORD_SIZE(%_ASM_BP)
+
+#ifdef CONFIG_X86_64
+	pop %r11
+	pop %r10
+	pop %r9
+	pop %r8
+	pop %rsi
+	pop %rdi
+#endif
+	pop %_ASM_DX
+	pop %_ASM_CX
+	pop %_ASM_AX
+	pop %_ASM_BP
+
+	ret
+ENDPROC(vmread_error_trampoline)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 04a8212..e177848 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -95,7 +95,7 @@
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
-static bool __read_mostly enable_apicv = 1;
+bool __read_mostly enable_apicv = 1;
 module_param(enable_apicv, bool, S_IRUGO);
 
 /*
@@ -648,43 +648,15 @@
 }
 
 #ifdef CONFIG_KEXEC_CORE
-/*
- * This bitmap is used to indicate whether the vmclear
- * operation is enabled on all cpus. All disabled by
- * default.
- */
-static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
-
-static inline void crash_enable_local_vmclear(int cpu)
-{
-	cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline void crash_disable_local_vmclear(int cpu)
-{
-	cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
-static inline int crash_local_vmclear_enabled(int cpu)
-{
-	return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
-}
-
 static void crash_vmclear_local_loaded_vmcss(void)
 {
 	int cpu = raw_smp_processor_id();
 	struct loaded_vmcs *v;
 
-	if (!crash_local_vmclear_enabled(cpu))
-		return;
-
 	list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
 			    loaded_vmcss_on_cpu_link)
 		vmcs_clear(v->vmcs);
 }
-#else
-static inline void crash_enable_local_vmclear(int cpu) { }
-static inline void crash_disable_local_vmclear(int cpu) { }
 #endif /* CONFIG_KEXEC_CORE */
 
 static void __loaded_vmcs_clear(void *arg)
@@ -696,19 +668,24 @@
 		return; /* vcpu migration can race with cpu offline */
 	if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
 		per_cpu(current_vmcs, cpu) = NULL;
-	crash_disable_local_vmclear(cpu);
+
+	vmcs_clear(loaded_vmcs->vmcs);
+	if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
+
 	list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
 
 	/*
-	 * we should ensure updating loaded_vmcs->loaded_vmcss_on_cpu_link
-	 * is before setting loaded_vmcs->vcpu to -1 which is done in
-	 * loaded_vmcs_init. Otherwise, other cpu can see vcpu = -1 fist
-	 * then adds the vmcs into percpu list before it is deleted.
+	 * Ensure all writes to loaded_vmcs, including deleting it from its
+	 * current percpu list, complete before setting loaded_vmcs->vcpu to
+	 * -1, otherwise a different cpu can see vcpu == -1 first and add
+	 * loaded_vmcs to its percpu list before it's deleted from this cpu's
+	 * list. Pairs with the smp_rmb() in vmx_vcpu_load_vmcs().
 	 */
 	smp_wmb();
 
-	loaded_vmcs_init(loaded_vmcs);
-	crash_enable_local_vmclear(cpu);
+	loaded_vmcs->cpu = -1;
+	loaded_vmcs->launched = 0;
 }
 
 void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
@@ -1153,6 +1130,10 @@
 					   vmx->guest_msrs[i].mask);
 
 	}
+
+    	if (vmx->nested.need_vmcs12_to_shadow_sync)
+		nested_sync_vmcs12_to_shadow(vcpu);
+
 	if (vmx->guest_state_loaded)
 		return;
 
@@ -1309,33 +1290,42 @@
 		pi_set_on(pi_desc);
 }
 
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu)
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
+			struct loaded_vmcs *buddy)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
+	struct vmcs *prev;
 
 	if (!already_loaded) {
 		loaded_vmcs_clear(vmx->loaded_vmcs);
 		local_irq_disable();
-		crash_disable_local_vmclear(cpu);
 
 		/*
-		 * Read loaded_vmcs->cpu should be before fetching
-		 * loaded_vmcs->loaded_vmcss_on_cpu_link.
-		 * See the comments in __loaded_vmcs_clear().
+		 * Ensure loaded_vmcs->cpu is read before adding loaded_vmcs to
+		 * this cpu's percpu list, otherwise it may not yet be deleted
+		 * from its previous cpu's percpu list.  Pairs with the
+		 * smb_wmb() in __loaded_vmcs_clear().
 		 */
 		smp_rmb();
 
 		list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
 			 &per_cpu(loaded_vmcss_on_cpu, cpu));
-		crash_enable_local_vmclear(cpu);
 		local_irq_enable();
 	}
 
-	if (per_cpu(current_vmcs, cpu) != vmx->loaded_vmcs->vmcs) {
+	prev = per_cpu(current_vmcs, cpu);
+	if (prev != vmx->loaded_vmcs->vmcs) {
 		per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
 		vmcs_load(vmx->loaded_vmcs->vmcs);
-		indirect_branch_prediction_barrier();
+
+		/*
+		 * No indirect branch prediction barrier needed when switching
+		 * the active VMCS within a guest, e.g. on nested VM-Enter.
+		 * The L1 VMM can protect itself with retpolines, IBPB or IBRS.
+		 */
+		if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev))
+			indirect_branch_prediction_barrier();
 	}
 
 	if (!already_loaded) {
@@ -1380,11 +1370,10 @@
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
-	vmx_vcpu_load_vmcs(vcpu, cpu);
+	vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
 
-	vmx->host_pkru = read_pkru();
 	vmx->host_debugctlmsr = get_debugctlmsr();
 }
 
@@ -1552,7 +1541,7 @@
 
 static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
-	unsigned long rip;
+	unsigned long rip, orig_rip;
 
 	/*
 	 * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on
@@ -1564,8 +1553,17 @@
 	 */
 	if (!static_cpu_has(X86_FEATURE_HYPERVISOR) ||
 	    to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) {
-		rip = kvm_rip_read(vcpu);
-		rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+		orig_rip = kvm_rip_read(vcpu);
+		rip = orig_rip + vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
+#ifdef CONFIG_X86_64
+		/*
+		 * We need to mask out the high 32 bits of RIP if not in 64-bit
+		 * mode, but just finding out that we are in 64-bit mode is
+		 * quite expensive.  Only do it if there was a carry.
+		 */
+		if (unlikely(((rip ^ orig_rip) >> 31) == 3) && !is_64_bit_mode(vcpu))
+			rip = (u32)rip;
+#endif
 		kvm_rip_write(vcpu, rip);
 	} else {
 		if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP))
@@ -1790,7 +1788,7 @@
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+		    !guest_has_spec_ctrl_msr(vcpu))
 			return 1;
 
 		msr_info->data = to_vmx(vcpu)->spec_ctrl;
@@ -1973,15 +1971,13 @@
 		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+		    !guest_has_spec_ctrl_msr(vcpu))
 			return 1;
 
-		/* The STIBP bit doesn't fault even if it's not advertised */
-		if (data & ~(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD))
+		if (kvm_spec_ctrl_test_value(data))
 			return 1;
 
 		vmx->spec_ctrl = data;
-
 		if (!data)
 			break;
 
@@ -2003,12 +1999,13 @@
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
+		    !guest_has_pred_cmd_msr(vcpu))
 			return 1;
 
 		if (data & ~PRED_CMD_IBPB)
 			return 1;
-
+		if (!boot_cpu_has(X86_FEATURE_IBPB))
+			return 1;
 		if (!data)
 			break;
 
@@ -2140,6 +2137,8 @@
 			(index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
 					PT_CAP_num_address_ranges)))
 			return 1;
+		if (is_noncanonical_address(data, vcpu))
+			return 1;
 		if (index % 2)
 			vmx->pt_desc.guest.addr_b[index / 2] = data;
 		else
@@ -2250,21 +2249,6 @@
 	    !hv_get_vp_assist_page(cpu))
 		return -EFAULT;
 
-	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
-	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-
-	/*
-	 * Now we can enable the vmclear operation in kdump
-	 * since the loaded_vmcss_on_cpu list on this cpu
-	 * has been initialized.
-	 *
-	 * Though the cpu is not in VMX operation now, there
-	 * is no problem to enable the vmclear operation
-	 * for the loaded_vmcss_on_cpu list is empty!
-	 */
-	crash_enable_local_vmclear(cpu);
-
 	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
 
 	test_bits = FEATURE_CONTROL_LOCKED;
@@ -2973,6 +2957,9 @@
 
 static int get_ept_level(struct kvm_vcpu *vcpu)
 {
+	/* Nested EPT currently only supports 4-level walks. */
+	if (is_guest_mode(vcpu) && nested_cpu_has_ept(get_vmcs12(vcpu)))
+		return 4;
 	if (cpu_has_vmx_ept_5levels() && (cpuid_maxphyaddr(vcpu) > 48))
 		return 5;
 	return 4;
@@ -2995,6 +2982,7 @@
 void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 {
 	struct kvm *kvm = vcpu->kvm;
+	bool update_guest_cr3 = true;
 	unsigned long guest_cr3;
 	u64 eptp;
 
@@ -3011,15 +2999,18 @@
 			spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
 		}
 
-		if (enable_unrestricted_guest || is_paging(vcpu) ||
-		    is_guest_mode(vcpu))
+		/* Loading vmcs02.GUEST_CR3 is handled by nested VM-Enter. */
+		if (is_guest_mode(vcpu))
+			update_guest_cr3 = false;
+		else if (enable_unrestricted_guest || is_paging(vcpu))
 			guest_cr3 = kvm_read_cr3(vcpu);
 		else
 			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
 		ept_load_pdptrs(vcpu);
 	}
 
-	vmcs_writel(GUEST_CR3, guest_cr3);
+	if (update_guest_cr3)
+		vmcs_writel(GUEST_CR3, guest_cr3);
 }
 
 int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
@@ -3844,24 +3835,29 @@
  * 2. If target vcpu isn't running(root mode), kick it to pick up the
  * interrupt from PIR in next vmentry.
  */
-static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
+static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int r;
 
 	r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
 	if (!r)
-		return;
+		return 0;
+
+	if (!vcpu->arch.apicv_active)
+		return -1;
 
 	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
-		return;
+		return 0;
 
 	/* If a previous notification has sent the IPI, nothing to do.  */
 	if (pi_test_and_set_on(&vmx->pi_desc))
-		return;
+		return 0;
 
 	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
+
+	return 0;
 }
 
 /*
@@ -3929,6 +3925,8 @@
 
 void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
 {
+	BUILD_BUG_ON(KVM_CR4_GUEST_OWNED_BITS & ~KVM_POSSIBLE_CR4_GUEST_BITS);
+
 	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
 	if (enable_ept)
 		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
@@ -4491,8 +4489,13 @@
 
 static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
-	return (!to_vmx(vcpu)->nested.nested_run_pending &&
-		vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+	if (to_vmx(vcpu)->nested.nested_run_pending)
+		return false;
+
+	if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
+		return true;
+
+	return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
 		!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
 			(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
 }
@@ -4586,7 +4589,7 @@
  */
 static void kvm_machine_check(void)
 {
-#if defined(CONFIG_X86_MCE) && defined(CONFIG_X86_64)
+#if defined(CONFIG_X86_MCE)
 	struct pt_regs regs = {
 		.cs = 3, /* Fake ring 3 no matter what the guest ran on */
 		.flags = X86_EFLAGS_IF,
@@ -5904,6 +5907,7 @@
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
 			exit_reason != EXIT_REASON_PML_FULL &&
+			exit_reason != EXIT_REASON_APIC_ACCESS &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -6438,23 +6442,6 @@
 					msrs[i].host, false);
 }
 
-static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx)
-{
-	u32 host_umwait_control;
-
-	if (!vmx_has_waitpkg(vmx))
-		return;
-
-	host_umwait_control = get_umwait_control_msr();
-
-	if (vmx->msr_ia32_umwait_control != host_umwait_control)
-		add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL,
-			vmx->msr_ia32_umwait_control,
-			host_umwait_control, false);
-	else
-		clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL);
-}
-
 static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6511,8 +6498,11 @@
 		vmcs_write32(PLE_WINDOW, vmx->ple_window);
 	}
 
-	if (vmx->nested.need_vmcs12_to_shadow_sync)
-		nested_sync_vmcs12_to_shadow(vcpu);
+	/*
+	 * We did this in prepare_switch_to_guest, because it needs to
+	 * be within srcu_read_lock.
+	 */
+	WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync);
 
 	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
 		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
@@ -6541,15 +6531,9 @@
 
 	kvm_load_guest_xcr0(vcpu);
 
-	if (static_cpu_has(X86_FEATURE_PKU) &&
-	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
-	    vcpu->arch.pkru != vmx->host_pkru)
-		__write_pkru(vcpu->arch.pkru);
-
 	pt_guest_enter(vmx);
 
 	atomic_switch_perf_msrs(vmx);
-	atomic_switch_umwait_control_msr(vmx);
 
 	if (enable_preemption_timer)
 		vmx_update_hv_timer(vcpu);
@@ -6634,18 +6618,6 @@
 
 	pt_guest_exit(vmx);
 
-	/*
-	 * eager fpu is enabled if PKEY is supported and CR4 is switched
-	 * back on host, so it is safe to read guest PKRU from current
-	 * XSAVE.
-	 */
-	if (static_cpu_has(X86_FEATURE_PKU) &&
-	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) {
-		vcpu->arch.pkru = rdpkru();
-		if (vcpu->arch.pkru != vmx->host_pkru)
-			__write_pkru(vmx->host_pkru);
-	}
-
 	kvm_put_guest_xcr0(vcpu);
 
 	vmx->nested.nested_run_pending = 0;
@@ -6670,6 +6642,10 @@
 	struct kvm_vmx *kvm_vmx = __vmalloc(sizeof(struct kvm_vmx),
 					    GFP_KERNEL_ACCOUNT | __GFP_ZERO,
 					    PAGE_KERNEL);
+
+	if (!kvm_vmx)
+		return NULL;
+
 	return &kvm_vmx->kvm;
 }
 
@@ -6793,8 +6769,7 @@
 
 	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
-					   vmx_capability.ept,
-					   kvm_vcpu_apicv_active(&vmx->vcpu));
+					   vmx_capability.ept);
 	else
 		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
 
@@ -6876,8 +6851,7 @@
 	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
 		return -EIO;
 	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
-					   enable_apicv);
+		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
 	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
 		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
 				smp_processor_id());
@@ -7123,6 +7097,40 @@
 	to_vmx(vcpu)->req_immediate_exit = true;
 }
 
+static int vmx_check_intercept_io(struct kvm_vcpu *vcpu,
+				  struct x86_instruction_info *info)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned short port;
+	bool intercept;
+	int size;
+
+	if (info->intercept == x86_intercept_in ||
+	    info->intercept == x86_intercept_ins) {
+		port = info->src_val;
+		size = info->dst_bytes;
+	} else {
+		port = info->dst_val;
+		size = info->src_bytes;
+	}
+
+	/*
+	 * If the 'use IO bitmaps' VM-execution control is 0, IO instruction
+	 * VM-exits depend on the 'unconditional IO exiting' VM-execution
+	 * control.
+	 *
+	 * Otherwise, IO instruction VM-exits are controlled by the IO bitmaps.
+	 */
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		intercept = nested_cpu_has(vmcs12,
+					   CPU_BASED_UNCOND_IO_EXITING);
+	else
+		intercept = nested_vmx_check_io_bitmaps(vcpu, port, size);
+
+	/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
+	return intercept ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE;
+}
+
 static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage)
@@ -7130,19 +7138,45 @@
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 
+	switch (info->intercept) {
 	/*
 	 * RDPID causes #UD if disabled through secondary execution controls.
 	 * Because it is marked as EmulateOnUD, we need to intercept it here.
 	 */
-	if (info->intercept == x86_intercept_rdtscp &&
-	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
-		ctxt->exception.vector = UD_VECTOR;
-		ctxt->exception.error_code_valid = false;
-		return X86EMUL_PROPAGATE_FAULT;
-	}
+	case x86_intercept_rdtscp:
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+			ctxt->exception.vector = UD_VECTOR;
+			ctxt->exception.error_code_valid = false;
+			return X86EMUL_PROPAGATE_FAULT;
+		}
+		break;
+
+	case x86_intercept_in:
+	case x86_intercept_ins:
+	case x86_intercept_out:
+	case x86_intercept_outs:
+		return vmx_check_intercept_io(vcpu, info);
+
+	case x86_intercept_lgdt:
+	case x86_intercept_lidt:
+	case x86_intercept_lldt:
+	case x86_intercept_ltr:
+	case x86_intercept_sgdt:
+	case x86_intercept_sidt:
+	case x86_intercept_sldt:
+	case x86_intercept_str:
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC))
+			return X86EMUL_CONTINUE;
+
+		/* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED.  */
+		break;
 
 	/* TODO: check more intercepts... */
-	return X86EMUL_CONTINUE;
+	default:
+		break;
+	}
+
+	return X86EMUL_UNHANDLEABLE;
 }
 
 #ifdef CONFIG_X86_64
@@ -7238,11 +7272,11 @@
 	kvm_flush_pml_buffers(kvm);
 }
 
-static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t gpa, dst;
+	gpa_t dst;
 
 	if (is_guest_mode(vcpu)) {
 		WARN_ON_ONCE(vmx->nested.pml_full);
@@ -7261,7 +7295,7 @@
 			return 1;
 		}
 
-		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+		gpa &= ~0xFFFull;
 		dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index;
 
 		if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,
@@ -7727,7 +7761,7 @@
 
 	if (nested) {
 		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
-					   vmx_capability.ept, enable_apicv);
+					   vmx_capability.ept);
 
 		r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
 		if (r)
@@ -7861,6 +7895,7 @@
 	.xsaves_supported = vmx_xsaves_supported,
 	.umip_emulated = vmx_umip_emulated,
 	.pt_supported = vmx_pt_supported,
+	.pku_supported = vmx_pku_supported,
 
 	.request_immediate_exit = vmx_request_immediate_exit,
 
@@ -7949,7 +7984,7 @@
 
 static int __init vmx_init(void)
 {
-	int r;
+	int r, cpu;
 
 #if IS_ENABLED(CONFIG_HYPERV)
 	/*
@@ -8003,6 +8038,12 @@
 		return r;
 	}
 
+	for_each_possible_cpu(cpu) {
+		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+		INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+		spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	}
+
 #ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
 			   crash_vmclear_local_loaded_vmcss);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 5a0f34b..55731dd 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -14,8 +14,6 @@
 extern const u32 vmx_msr_index[];
 extern u64 host_efer;
 
-extern u32 get_umwait_control_msr(void);
-
 #define MSR_TYPE_R	1
 #define MSR_TYPE_W	2
 #define MSR_TYPE_RW	3
@@ -304,7 +302,8 @@
 };
 
 bool nested_vmx_allowed(struct kvm_vcpu *vcpu);
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu);
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
+			struct loaded_vmcs *buddy);
 void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 int allocate_vpid(void);
 void free_vpid(int vpid);
@@ -513,7 +512,7 @@
 
 static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx)
 {
-	return vmx->secondary_exec_control &
+	return secondary_exec_controls_get(vmx) &
 		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5d53052..f1a0eeb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -92,6 +92,8 @@
 static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #endif
 
+static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
+
 #define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
 #define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
@@ -100,6 +102,7 @@
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
+static void process_smi(struct kvm_vcpu *vcpu);
 static void enter_smm(struct kvm_vcpu *vcpu);
 static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 static void store_regs(struct kvm_vcpu *vcpu);
@@ -205,7 +208,6 @@
 	{ "l1d_flush", VCPU_STAT(l1d_flush) },
 	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
 	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
-	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
 	{ "mmu_pde_zapped", VM_STAT(mmu_pde_zapped) },
 	{ "mmu_flooded", VM_STAT(mmu_flooded) },
 	{ "mmu_recycled", VM_STAT(mmu_recycled) },
@@ -300,13 +302,14 @@
 	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 	int err;
 
-	if (((value ^ smsr->values[slot].curr) & mask) == 0)
+	value = (value & mask) | (smsr->values[slot].host & ~mask);
+	if (value == smsr->values[slot].curr)
 		return 0;
-	smsr->values[slot].curr = value;
 	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
 	if (err)
 		return 1;
 
+	smsr->values[slot].curr = value;
 	if (!smsr->registered) {
 		smsr->urn.on_user_return = kvm_on_user_return;
 		user_return_notifier_register(&smsr->urn);
@@ -442,6 +445,14 @@
 		 * for #DB exceptions under VMX.
 		 */
 		vcpu->arch.dr6 ^= payload & DR6_RTM;
+
+		/*
+		 * The #DB payload is defined as compatible with the 'pending
+		 * debug exceptions' field under VMX, not DR6. While bit 12 is
+		 * defined in the 'pending debug exceptions' field (enabled
+		 * breakpoint), it is reserved and must be zero in DR6.
+		 */
+		vcpu->arch.dr6 &= ~BIT(12);
 		break;
 	case PF_VECTOR:
 		vcpu->arch.cr2 = payload;
@@ -464,8 +475,6 @@
 
 	if (!vcpu->arch.exception.pending && !vcpu->arch.exception.injected) {
 	queue:
-		if (has_error && !is_protmode(vcpu))
-			has_error = false;
 		if (reinject) {
 			/*
 			 * On vmentry, vcpu->arch.exception.pending is only
@@ -821,11 +830,25 @@
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
 		vcpu->guest_xcr0_loaded = 1;
 	}
+
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) &&
+	    vcpu->arch.pkru != vcpu->arch.host_pkru)
+		__write_pkru(vcpu->arch.pkru);
 }
 EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
 
 void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 {
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
+	     (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
+		vcpu->arch.pkru = rdpkru();
+		if (vcpu->arch.pkru != vcpu->arch.host_pkru)
+			__write_pkru(vcpu->arch.host_pkru);
+	}
+
 	if (vcpu->guest_xcr0_loaded) {
 		if (vcpu->arch.xcr0 != host_xcr0)
 			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
@@ -885,9 +908,38 @@
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
+static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c)
+{
+	u64 reserved_bits = CR4_RESERVED_BITS;
+
+	if (!cpu_has(c, X86_FEATURE_XSAVE))
+		reserved_bits |= X86_CR4_OSXSAVE;
+
+	if (!cpu_has(c, X86_FEATURE_SMEP))
+		reserved_bits |= X86_CR4_SMEP;
+
+	if (!cpu_has(c, X86_FEATURE_SMAP))
+		reserved_bits |= X86_CR4_SMAP;
+
+	if (!cpu_has(c, X86_FEATURE_FSGSBASE))
+		reserved_bits |= X86_CR4_FSGSBASE;
+
+	if (!cpu_has(c, X86_FEATURE_PKU))
+		reserved_bits |= X86_CR4_PKE;
+
+	if (!cpu_has(c, X86_FEATURE_LA57) &&
+	    !(cpuid_ecx(0x7) & bit(X86_FEATURE_LA57)))
+		reserved_bits |= X86_CR4_LA57;
+
+	if (!cpu_has(c, X86_FEATURE_UMIP) && !kvm_x86_ops->umip_emulated())
+		reserved_bits |= X86_CR4_UMIP;
+
+	return reserved_bits;
+}
+
 static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	if (cr4 & CR4_RESERVED_BITS)
+	if (cr4 & cr4_reserved_bits)
 		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
@@ -918,7 +970,8 @@
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
-				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
+				   X86_CR4_SMEP;
+	unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
 
 	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
@@ -926,6 +979,8 @@
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE))
 			return 1;
+		if ((cr4 ^ old_cr4) & X86_CR4_LA57)
+			return 1;
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
@@ -944,7 +999,7 @@
 	if (kvm_x86_ops->set_cr4(vcpu, cr4))
 		return 1;
 
-	if (((cr4 ^ old_cr4) & pdptr_bits) ||
+	if (((cr4 ^ old_cr4) & mmu_role_bits) ||
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
@@ -1053,9 +1108,11 @@
 
 static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 {
+	size_t size = ARRAY_SIZE(vcpu->arch.db);
+
 	switch (dr) {
 	case 0 ... 3:
-		vcpu->arch.db[dr] = val;
+		vcpu->arch.db[array_index_nospec(dr, size)] = val;
 		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
 			vcpu->arch.eff_db[dr] = val;
 		break;
@@ -1092,9 +1149,11 @@
 
 int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
 {
+	size_t size = ARRAY_SIZE(vcpu->arch.db);
+
 	switch (dr) {
 	case 0 ... 3:
-		*val = vcpu->arch.db[dr];
+		*val = vcpu->arch.db[array_index_nospec(dr, size)];
 		break;
 	case 4:
 		/* fall through */
@@ -1327,10 +1386,15 @@
 	 * If TSX is disabled on the system, guests are also mitigated against
 	 * TAA and clear CPU buffer mitigation is not required for guests.
 	 */
-	if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
-	    (data & ARCH_CAP_TSX_CTRL_MSR))
+	if (!boot_cpu_has(X86_FEATURE_RTM))
+		data &= ~ARCH_CAP_TAA_NO;
+	else if (!boot_cpu_has_bug(X86_BUG_TAA))
+		data |= ARCH_CAP_TAA_NO;
+	else if (data & ARCH_CAP_TSX_CTRL_MSR)
 		data &= ~ARCH_CAP_MDS_NO;
 
+	/* KVM does not emulate MSR_IA32_TSX_CTRL.  */
+	data &= ~ARCH_CAP_TSX_CTRL_MSR;
 	return data;
 }
 
@@ -2484,7 +2548,10 @@
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MCx_CTL(bank_num)) {
-			u32 offset = msr - MSR_IA32_MC0_CTL;
+			u32 offset = array_index_nospec(
+				msr - MSR_IA32_MC0_CTL,
+				MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
 			/* only 0 or all 1s can be written to IA32_MCi_CTL
 			 * some Linux kernels though clear bit 10 in bank 4 to
 			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
@@ -2580,45 +2647,47 @@
 
 static void record_steal_time(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
+	/* -EAGAIN is returned in atomic context so we can just return. */
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT,
+			&map, &vcpu->arch.st.cache, false))
 		return;
 
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+
 	/*
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
 	 * expensive IPIs.
 	 */
 	trace_kvm_pv_tlb_flush(vcpu->vcpu_id,
-		vcpu->arch.st.steal.preempted & KVM_VCPU_FLUSH_TLB);
-	if (xchg(&vcpu->arch.st.steal.preempted, 0) & KVM_VCPU_FLUSH_TLB)
+		st->preempted & KVM_VCPU_FLUSH_TLB);
+	if (xchg(&st->preempted, 0) & KVM_VCPU_FLUSH_TLB)
 		kvm_vcpu_flush_tlb(vcpu, false);
 
-	if (vcpu->arch.st.steal.version & 1)
-		vcpu->arch.st.steal.version += 1;  /* first time write, random junk */
+	vcpu->arch.st.preempted = 0;
 
-	vcpu->arch.st.steal.version += 1;
+	if (st->version & 1)
+		st->version += 1;  /* first time write, random junk */
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	st->version += 1;
 
 	smp_wmb();
 
-	vcpu->arch.st.steal.steal += current->sched_info.run_delay -
+	st->steal += current->sched_info.run_delay -
 		vcpu->arch.st.last_steal;
 	vcpu->arch.st.last_steal = current->sched_info.run_delay;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
-
 	smp_wmb();
 
-	vcpu->arch.st.steal.version += 1;
+	st->version += 1;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
-		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false);
 }
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
@@ -2685,7 +2754,7 @@
 		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
 		return kvm_set_apic_base(vcpu, msr_info);
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSCDEADLINE:
 		kvm_set_lapic_tscdeadline_msr(vcpu, data);
@@ -2695,6 +2764,10 @@
 			if (!msr_info->host_initiated) {
 				s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
 				adjust_tsc_offset_guest(vcpu, adj);
+				/* Before back to guest, tsc_timestamp must be adjusted
+				 * as well, otherwise guest's percpu pvclock time could jump.
+				 */
+				kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 			}
 			vcpu->arch.ia32_tsc_adjust_msr = data;
 		}
@@ -2771,11 +2844,6 @@
 		if (data & KVM_STEAL_RESERVED_MASK)
 			return 1;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
-						data & KVM_STEAL_VALID_BITS,
-						sizeof(struct kvm_steal_time)))
-			return 1;
-
 		vcpu->arch.st.msr_val = data;
 
 		if (!(data & KVM_MSR_ENABLED))
@@ -2911,7 +2979,10 @@
 	default:
 		if (msr >= MSR_IA32_MC0_CTL &&
 		    msr < MSR_IA32_MCx_CTL(bank_num)) {
-			u32 offset = msr - MSR_IA32_MC0_CTL;
+			u32 offset = array_index_nospec(
+				msr - MSR_IA32_MC0_CTL,
+				MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
 			data = vcpu->arch.mce_banks[offset];
 			break;
 		}
@@ -2991,7 +3062,7 @@
 	case MSR_IA32_APICBASE:
 		msr_info->data = kvm_get_apic_base(vcpu);
 		break;
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
 		break;
 	case MSR_IA32_TSCDEADLINE:
@@ -3437,10 +3508,6 @@
 
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
 
-	fpregs_assert_state_consistent();
-	if (test_thread_flag(TIF_NEED_FPU_LOAD))
-		switch_fpu_return();
-
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
@@ -3480,15 +3547,25 @@
 
 static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 {
+	struct kvm_host_map map;
+	struct kvm_steal_time *st;
+
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	vcpu->arch.st.steal.preempted = KVM_VCPU_PREEMPTED;
+	if (vcpu->arch.st.preempted)
+		return;
 
-	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
-			&vcpu->arch.st.steal.preempted,
-			offsetof(struct kvm_steal_time, preempted),
-			sizeof(vcpu->arch.st.steal.preempted));
+	if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map,
+			&vcpu->arch.st.cache, true))
+		return;
+
+	st = map.hva +
+		offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
+
+	st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
+
+	kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -3549,22 +3626,33 @@
 
 static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * We can accept userspace's request for interrupt injection
+	 * as long as we have a place to store the interrupt number.
+	 * The actual injection will happen when the CPU is able to
+	 * deliver the interrupt.
+	 */
+	if (kvm_cpu_has_extint(vcpu))
+		return false;
+
+	/* Acknowledging ExtINT does not happen if LINT0 is masked.  */
 	return (!lapic_in_kernel(vcpu) ||
 		kvm_apic_accept_pic_intr(vcpu));
 }
 
-/*
- * if userspace requested an interrupt window, check that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
 {
-	return kvm_arch_interrupt_allowed(vcpu) &&
-		!kvm_cpu_has_interrupt(vcpu) &&
+	/*
+	 * Do not cause an interrupt window exit if an exception
+	 * is pending or an event needs reinjection; userspace
+	 * might want to inject the interrupt manually using KVM_SET_REGS
+	 * or KVM_SET_SREGS.  For that to work, we must be at an
+	 * instruction boundary and with no events half-injected.
+	 */
+	return (kvm_arch_interrupt_allowed(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu) &&
 		!kvm_event_needs_reinjection(vcpu) &&
-		kvm_cpu_accept_dm_intr(vcpu);
+		!vcpu->arch.exception.pending);
 }
 
 static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
@@ -3624,7 +3712,7 @@
 	unsigned bank_num = mcg_cap & 0xff, bank;
 
 	r = -EINVAL;
-	if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
+	if (!bank_num || bank_num > KVM_MAX_MCE_BANKS)
 		goto out;
 	if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000))
 		goto out;
@@ -3695,6 +3783,10 @@
 {
 	process_nmi(vcpu);
 
+
+	if (kvm_check_request(KVM_REQ_SMI, vcpu))
+		process_smi(vcpu);
+
 	/*
 	 * The API doesn't provide the instruction length for software
 	 * exceptions, so don't report them. As long as the guest RIP
@@ -4421,6 +4513,7 @@
 	case KVM_SET_NESTED_STATE: {
 		struct kvm_nested_state __user *user_kvm_nested_state = argp;
 		struct kvm_nested_state kvm_state;
+		int idx;
 
 		r = -EINVAL;
 		if (!kvm_x86_ops->set_nested_state)
@@ -4444,7 +4537,9 @@
 		    && !(kvm_state.flags & KVM_STATE_NESTED_GUEST_MODE))
 			break;
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_x86_ops->set_nested_state(vcpu, user_kvm_nested_state, &kvm_state);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_GET_SUPPORTED_HV_CPUID: {
@@ -4973,10 +5068,13 @@
 		r = -EFAULT;
 		if (copy_from_user(&u.ps, argp, sizeof(u.ps)))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit_out;
 		r = kvm_vm_ioctl_set_pit(kvm, &u.ps);
+set_pit_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_GET_PIT2: {
@@ -4996,10 +5094,13 @@
 		r = -EFAULT;
 		if (copy_from_user(&u.ps2, argp, sizeof(u.ps2)))
 			goto out;
+		mutex_lock(&kvm->lock);
 		r = -ENXIO;
 		if (!kvm->arch.vpit)
-			goto out;
+			goto set_pit2_out;
 		r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2);
+set_pit2_out:
+		mutex_unlock(&kvm->lock);
 		break;
 	}
 	case KVM_REINJECT_CONTROL: {
@@ -5151,6 +5252,10 @@
 			if (!kvm_x86_ops->rdtscp_supported())
 				continue;
 			break;
+		case MSR_IA32_UMWAIT_CONTROL:
+			if (!boot_cpu_has(X86_FEATURE_WAITPKG))
+				continue;
+			break;
 		case MSR_IA32_RTIT_CTL:
 		case MSR_IA32_RTIT_STATUS:
 			if (!kvm_x86_ops->pt_supported())
@@ -6185,7 +6290,10 @@
 
 static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
 {
-	emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+	vcpu->arch.hflags = emul_flags;
+	kvm_mmu_reset_context(vcpu);
 }
 
 static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
@@ -6356,11 +6464,11 @@
 	return 1;
 }
 
-static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 				  bool write_fault_to_shadow_pgtable,
 				  int emulation_type)
 {
-	gpa_t gpa = cr2;
+	gpa_t gpa = cr2_or_gpa;
 	kvm_pfn_t pfn;
 
 	if (!(emulation_type & EMULTYPE_ALLOW_RETRY))
@@ -6374,7 +6482,7 @@
 		 * Write permission should be allowed since only
 		 * write access need to be emulated.
 		 */
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 		/*
 		 * If the mapping is invalid in guest, let cpu retry
@@ -6431,10 +6539,10 @@
 }
 
 static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
-			      unsigned long cr2,  int emulation_type)
+			      gpa_t cr2_or_gpa,  int emulation_type)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-	unsigned long last_retry_eip, last_retry_addr, gpa = cr2;
+	unsigned long last_retry_eip, last_retry_addr, gpa = cr2_or_gpa;
 
 	last_retry_eip = vcpu->arch.last_retry_eip;
 	last_retry_addr = vcpu->arch.last_retry_addr;
@@ -6463,14 +6571,14 @@
 	if (x86_page_table_writing_insn(ctxt))
 		return false;
 
-	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2)
+	if (ctxt->eip == last_retry_eip && last_retry_addr == cr2_or_gpa)
 		return false;
 
 	vcpu->arch.last_retry_eip = ctxt->eip;
-	vcpu->arch.last_retry_addr = cr2;
+	vcpu->arch.last_retry_addr = cr2_or_gpa;
 
 	if (!vcpu->arch.mmu->direct_map)
-		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2_or_gpa, NULL);
 
 	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
 
@@ -6616,11 +6724,8 @@
 	return false;
 }
 
-int x86_emulate_instruction(struct kvm_vcpu *vcpu,
-			    unsigned long cr2,
-			    int emulation_type,
-			    void *insn,
-			    int insn_len)
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+			    int emulation_type, void *insn, int insn_len)
 {
 	int r;
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
@@ -6666,8 +6771,9 @@
 				kvm_queue_exception(vcpu, UD_VECTOR);
 				return 1;
 			}
-			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
-						emulation_type))
+			if (reexecute_instruction(vcpu, cr2_or_gpa,
+						  write_fault_to_spt,
+						  emulation_type))
 				return 1;
 			if (ctxt->have_exception) {
 				/*
@@ -6701,7 +6807,7 @@
 		return 1;
 	}
 
-	if (retry_instruction(ctxt, cr2, emulation_type))
+	if (retry_instruction(ctxt, cr2_or_gpa, emulation_type))
 		return 1;
 
 	/* this is needed for vmware backdoor interface to work since it
@@ -6713,7 +6819,7 @@
 
 restart:
 	/* Save the faulting GPA (cr2) in the address field */
-	ctxt->exception.address = cr2;
+	ctxt->exception.address = cr2_or_gpa;
 
 	r = x86_emulate_insn(ctxt);
 
@@ -6721,7 +6827,7 @@
 		return 1;
 
 	if (r == EMULATION_FAILED) {
-		if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
+		if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt,
 					emulation_type))
 			return 1;
 
@@ -6760,7 +6866,7 @@
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
 			kvm_rip_write(vcpu, ctxt->eip);
-			if (r && ctxt->tf)
+			if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
 				r = kvm_vcpu_do_singlestep(vcpu);
 			__kvm_set_rflags(vcpu, ctxt->eflags);
 		}
@@ -7264,6 +7370,7 @@
 	cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
 #ifdef CONFIG_X86_64
 	pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
+	cancel_work_sync(&pvclock_gtod_work);
 #endif
 	kvm_x86_ops = NULL;
 	kvm_mmu_module_exit();
@@ -7496,14 +7603,21 @@
 	kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
 }
 
-static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
+static void kvm_inject_exception(struct kvm_vcpu *vcpu)
+{
+       if (vcpu->arch.exception.error_code && !is_protmode(vcpu))
+               vcpu->arch.exception.error_code = false;
+       kvm_x86_ops->queue_exception(vcpu);
+}
+
+static int inject_pending_event(struct kvm_vcpu *vcpu)
 {
 	int r;
 
 	/* try to reinject previous events if any */
 
 	if (vcpu->arch.exception.injected)
-		kvm_x86_ops->queue_exception(vcpu);
+		kvm_inject_exception(vcpu);
 	/*
 	 * Do not inject an NMI or interrupt if there is a pending
 	 * exception.  Exceptions and interrupts are recognized at
@@ -7532,7 +7646,7 @@
 	 * from L2 to L1.
 	 */
 	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
-		r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+		r = kvm_x86_ops->check_nested_events(vcpu);
 		if (r != 0)
 			return r;
 	}
@@ -7569,7 +7683,7 @@
 			}
 		}
 
-		kvm_x86_ops->queue_exception(vcpu);
+		kvm_inject_exception(vcpu);
 	}
 
 	/* Don't consider new event if we re-injected an event */
@@ -7594,7 +7708,7 @@
 		 * KVM_REQ_EVENT only on certain events and not unconditionally?
 		 */
 		if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
-			r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+			r = kvm_x86_ops->check_nested_events(vcpu);
 			if (r != 0)
 				return r;
 		}
@@ -7905,9 +8019,8 @@
 	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
 }
 
-int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-		unsigned long start, unsigned long end,
-		bool blockable)
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+					    unsigned long start, unsigned long end)
 {
 	unsigned long apic_address;
 
@@ -7918,8 +8031,6 @@
 	apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
 	if (start <= apic_address && apic_address < end)
 		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
-
-	return 0;
 }
 
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
@@ -8071,7 +8182,7 @@
 			goto out;
 		}
 
-		if (inject_pending_event(vcpu, req_int_win) != 0)
+		if (inject_pending_event(vcpu) != 0)
 			req_immediate_exit = true;
 		else {
 			/* Enable SMI/NMI/IRQ window open exits if needed.
@@ -8163,8 +8274,12 @@
 	trace_kvm_entry(vcpu->vcpu_id);
 	guest_enter_irqoff();
 
-	/* The preempt notifier should have taken care of the FPU already.  */
-	WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD));
+	/* Save host pkru register if supported */
+	vcpu->arch.host_pkru = read_pkru();
+
+	fpregs_assert_state_consistent();
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		switch_fpu_return();
 
 	if (unlikely(vcpu->arch.switch_db_regs)) {
 		set_debugreg(0, 7);
@@ -8174,6 +8289,8 @@
 		set_debugreg(vcpu->arch.eff_db[3], 3);
 		set_debugreg(vcpu->arch.dr6, 6);
 		vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
+	} else if (unlikely(hw_breakpoint_active())) {
+		set_debugreg(0, 7);
 	}
 
 	kvm_x86_ops->run(vcpu);
@@ -8300,7 +8417,7 @@
 static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
 {
 	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events)
-		kvm_x86_ops->check_nested_events(vcpu, false);
+		kvm_x86_ops->check_nested_events(vcpu);
 
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
 		!vcpu->arch.apf.halted);
@@ -8436,12 +8553,26 @@
 	return 0;
 }
 
+static void kvm_save_current_fpu(struct fpu *fpu)
+{
+	/*
+	 * If the target FPU state is not resident in the CPU registers, just
+	 * memcpy() from current, else save CPU state directly to the target.
+	 */
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		memcpy(&fpu->state, &current->thread.fpu.state,
+		       fpu_kernel_xstate_size);
+	else
+		copy_fpregs_to_fpstate(fpu);
+}
+
 /* Swap (qemu) user FPU context for the guest FPU context. */
 static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(vcpu->arch.user_fpu);
+	kvm_save_current_fpu(vcpu->arch.user_fpu);
+
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
 				~XFEATURE_MASK_PKRU);
@@ -8457,7 +8588,8 @@
 {
 	fpregs_lock();
 
-	copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
+	kvm_save_current_fpu(vcpu->arch.guest_fpu);
+
 	copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
 
 	fpregs_mark_activate();
@@ -8679,6 +8811,8 @@
 				    struct kvm_mp_state *mp_state)
 {
 	vcpu_load(vcpu);
+	if (kvm_mpx_supported())
+		kvm_load_guest_fpu(vcpu);
 
 	kvm_apic_accept_events(vcpu);
 	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
@@ -8687,6 +8821,8 @@
 	else
 		mp_state->mp_state = vcpu->arch.mp_state;
 
+	if (kvm_mpx_supported())
+		kvm_put_guest_fpu(vcpu);
 	vcpu_put(vcpu);
 	return 0;
 }
@@ -9046,6 +9182,9 @@
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+	struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache;
+
+	kvm_release_pfn(cache->pfn, cache->dirty, cache);
 
 	kvmclock_reset(vcpu);
 
@@ -9110,13 +9249,7 @@
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.apf.msr_val = 0;
-
-	vcpu_load(vcpu);
-	kvm_mmu_unload(vcpu);
-	vcpu_put(vcpu);
-
-	kvm_x86_ops->vcpu_free(vcpu);
+	kvm_arch_vcpu_free(vcpu);
 }
 
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -9308,6 +9441,8 @@
 	if (r != 0)
 		return r;
 
+	cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data);
+
 	if (kvm_has_tsc_control) {
 		/*
 		 * Make sure the user can only configure tsc_khz values that
@@ -9648,6 +9783,13 @@
 {
 	int i;
 
+	/*
+	 * Clear out the previous array pointers for the KVM_MR_MOVE case.  The
+	 * old arrays will be freed by __kvm_set_memory_region() if installing
+	 * the new memslot is successful.
+	 */
+	memset(&slot->arch, 0, sizeof(slot->arch));
+
 	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
 		struct kvm_lpage_info *linfo;
 		unsigned long ugfn;
@@ -9710,11 +9852,18 @@
 
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen)
 {
+	struct kvm_vcpu *vcpu;
+	int i;
+
 	/*
 	 * memslots->generation has been incremented.
 	 * mmio generation may have reached its maximum value.
 	 */
 	kvm_mmu_invalidate_mmio_sptes(kvm, gen);
+
+	/* Force re-initialization of steal_time cache */
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_vcpu_kick(vcpu);
 }
 
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -9722,6 +9871,10 @@
 				const struct kvm_userspace_memory_region *mem,
 				enum kvm_mr_change change)
 {
+	if (change == KVM_MR_MOVE)
+		return kvm_arch_create_memslot(kvm, memslot,
+					       mem->memory_size >> PAGE_SHIFT);
+
 	return 0;
 }
 
@@ -9966,7 +10119,7 @@
 	      work->arch.cr3 != vcpu->arch.mmu->get_cr3(vcpu))
 		return;
 
-	vcpu->arch.mmu->page_fault(vcpu, work->gva, 0, true);
+	vcpu->arch.mmu->page_fault(vcpu, work->cr2_or_gpa, 0, true);
 }
 
 static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
@@ -10079,7 +10232,7 @@
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_not_present(work->arch.token, work->gva);
+	trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
 	kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
 
 	if (kvm_can_deliver_async_pf(vcpu) &&
@@ -10114,7 +10267,7 @@
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
+	trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa);
 
 	if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
 	    !apf_get_user(vcpu, &val)) {
@@ -10245,6 +10398,32 @@
 EXPORT_SYMBOL_GPL(kvm_arch_no_poll);
 
 
+int kvm_spec_ctrl_test_value(u64 value)
+{
+	/*
+	 * test that setting IA32_SPEC_CTRL to given value
+	 * is allowed by the host processor
+	 */
+
+	u64 saved_value;
+	unsigned long flags;
+	int ret = 0;
+
+	local_irq_save(flags);
+
+	if (rdmsrl_safe(MSR_IA32_SPEC_CTRL, &saved_value))
+		ret = 1;
+	else if (wrmsrl_safe(MSR_IA32_SPEC_CTRL, value))
+		ret = 1;
+	else
+		wrmsrl(MSR_IA32_SPEC_CTRL, saved_value);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index dbf7442..c520d37 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -286,7 +286,7 @@
 bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 					  int page_num);
 bool kvm_vector_hashing_enabled(void);
-int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
+int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			    int emulation_type, void *insn, int insn_len);
 
 #define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
@@ -368,5 +368,6 @@
 
 void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
 void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
+int kvm_spec_ctrl_test_value(u64 value);
 
 #endif